Computer Vision and Pattern Recognition (cs.CV)

Abstract: Knowledge Distillation (KD) is a powerful technique for transferring knowledge between neural network models, where a pre-trained teacher model is used to facilitate the training of the target student model. However, the availability of a suitable teacher model is not always guaranteed. To address this challenge, Self-Knowledge Distillation (SKD) attempts to construct a teacher model from itself. Existing SKD methods add Auxiliary Classifiers (AC) to intermediate layers of the model or use the history models and models with different input data within the same class. However, these methods are computationally expensive and only capture time-wise and class-wise features of data. In this paper, we propose a lightweight SKD framework that utilizes multi-source information to construct a more informative teacher. Specifically, we introduce a Distillation with Reverse Guidance (DRG) method that considers different levels of information extracted by the model, including edge, shape, and detail of the input data, to construct a more informative teacher. Additionally, we design a Distillation with Shape-wise Regularization (DSR) method that ensures a consistent shape of ranked model output for all data. We validate the performance of the proposed DRG, DSR, and their combination through comprehensive experiments on various datasets and models. Our results demonstrate the superiority of the proposed methods over baselines (up to 2.87%) and state-of-the-art SKD methods (up to 1.15%), while being computationally efficient and robust. The code is available at https://github.com/xucong-parsifal/LightSKD.

Abstract: 3D LiDAR-based single object tracking (SOT) has gained increasing attention as it plays a crucial role in 3D applications such as autonomous driving. The central problem is how to learn a target-aware representation from the sparse and incomplete point clouds. In this paper, we propose a novel Correlation Pyramid Network (CorpNet) with a unified encoder and a motion-factorized decoder. Specifically, the encoder introduces multi-level self attentions and cross attentions in its main branch to enrich the template and search region features and realize their fusion and interaction, respectively. Additionally, considering the sparsity characteristics of the point clouds, we design a lateral correlation pyramid structure for the encoder to keep as many points as possible by integrating hierarchical correlated features. The output features of the search region from the encoder can be directly fed into the decoder for predicting target locations without any extra matcher. Moreover, in the decoder of CorpNet, we design a motion-factorized head to explicitly learn the different movement patterns of the up axis and the x-y plane together. Extensive experiments on two commonly-used datasets show our CorpNet achieves state-of-the-art results while running in real-time.

Abstract: Digital images contain a lot of redundancies, therefore, compression techniques are applied to reduce the image size without loss of reasonable image quality. Same become more prominent in the case of videos which contains image sequences and higher compression ratios are achieved in low throughput networks. Assessment of quality of images in such scenarios has become of particular interest. Subjective evaluation in most of the scenarios is infeasible so objective evaluation is preferred. Among the three objective quality measures, full-reference and reduced-reference methods require an original image in some form to calculate the image quality which is unfeasible in scenarios such as broadcasting, acquisition or enhancement. Therefore, a no-reference Perceptual Image Quality Index (PIQI) is proposed in this paper to assess the quality of digital images which calculates luminance and gradient statistics along with mean subtracted contrast normalized products in multiple scales and color spaces. These extracted features are provided to a stacked ensemble of Gaussian Process Regression (GPR) to perform the perceptual quality evaluation. The performance of the PIQI is checked on six benchmark databases and compared with twelve state-of-the-art methods and competitive results are achieved. The comparison is made based on RMSE, Pearson and Spearman correlation coefficients between ground truth and predicted quality scores. The scores of 0.0552, 0.9802 and 0.9776 are achieved respectively for these metrics on CSIQ database. Two cross-dataset evaluation experiments are performed to check the generalization of PIQI.

Abstract: Band selection has a great impact on the spectral recovery quality. To solve this ill-posed inverse problem, most band selection methods adopt hand-crafted priors or exploit clustering or sparse regularization constraints to find most prominent bands. These methods are either very slow due to the computational cost of repeatedly training with respect to different selection frequencies or different band combinations. Many traditional methods rely on the scene prior and thus are not applicable to other scenarios. In this paper, we present a novel one-shot Neural Band Selection (NBS) framework for spectral recovery. Unlike conventional searching approaches with a discrete search space and a non-differentiable search strategy, our NBS is based on the continuous relaxation of the band selection process, thus allowing efficient band search using gradient descent. To enable the compatibility for se- lecting any number of bands in one-shot, we further exploit the band-wise correlation matrices to progressively suppress similar adjacent bands. Extensive evaluations on the NTIRE 2022 Spectral Reconstruction Challenge demonstrate that our NBS achieves consistent performance gains over competitive baselines when examined with four different spectral recov- ery methods. Our code will be publicly available.

Abstract: Online continual learning (OCL) research has primarily focused on mitigating catastrophic forgetting with fixed and limited storage allocation throughout the agent's lifetime. However, the growing affordability of data storage highlights a broad range of applications that do not adhere to these assumptions. In these cases, the primary concern lies in managing computational expenditures rather than storage. In this paper, we target such settings, investigating the online continual learning problem by relaxing storage constraints and emphasizing fixed, limited economical budget. We provide a simple algorithm that can compactly store and utilize the entirety of the incoming data stream under tiny computational budgets using a kNN classifier and universal pre-trained feature extractors. Our algorithm provides a consistency property attractive to continual learning: It will never forget past seen data. We set a new state of the art on two large-scale OCL datasets: Continual LOCalization (CLOC), which has 39M images over 712 classes, and Continual Google Landmarks V2 (CGLM), which has 580K images over 10,788 classes -- beating methods under far higher computational budgets than ours in terms of both reducing catastrophic forgetting of past data and quickly adapting to rapidly changing data streams. We provide code to reproduce our results at \url{https://github.com/drimpossible/ACM}.

Abstract: The increasing prevalence of gigapixel resolutions has presented new challenges for crowd counting. Such resolutions are far beyond the memory and computation limits of current GPUs, and available deep neural network architectures and training procedures are not designed for such massive inputs. Although several methods have been proposed to address these challenges, they are either limited to downsampling the input image to a small size, or borrowing from other gigapixel tasks, which are not tailored for crowd counting. In this paper, we propose a novel method called GigaZoom, which iteratively zooms into the densest areas of the image and refines coarser density maps with finer details. Through experiments, we show that GigaZoom obtains the state-of-the-art for gigapixel crowd counting and improves the accuracy of the next best method by 42%.

Abstract: In which we propose neural network architecture (dune neural network) for recognizing general noisy image without adding any artificial noise in the training data. By representing each free parameter of the network as an uncertainty interval, and applying a linear transformation to each input element, we show that the resulting architecture achieves decent noise robustness when faced with input data with white noise. We apply simple dune neural networks for MNIST dataset and demonstrate that even for very noisy input images which are hard for human to recognize, our approach achieved better test set accuracy than human without dataset augmentation. We also find that our method is robust for many other examples with various background patterns added.

Abstract: With the development of deep learning, the field of face anti-spoofing (FAS) has witnessed great progress. FAS is usually considered a classification problem, where each class is assumed to contain a single cluster optimized by softmax loss. In practical deployment, one class can contain several local clusters, and a single-center is insufficient to capture the inherent structure of the FAS data. However, few approaches consider large distribution discrepancies in the field of FAS. In this work, we propose a unified framework called Latent Distribution Adjusting (LDA) with properties of latent, discriminative, adaptive, generic to improve the robustness of the FAS model by adjusting complex data distribution with multiple prototypes. 1) Latent. LDA attempts to model the data of each class as a Gaussian mixture distribution, and acquire a flexible number of centers for each class in the last fully connected layer implicitly. 2) Discriminative. To enhance the intra-class compactness and inter-class discrepancy, we propose a margin-based loss for providing distribution constrains for prototype learning. 3) Adaptive. To make LDA more efficient and decrease redundant parameters, we propose Adaptive Prototype Selection (APS) by selecting the appropriate number of centers adaptively according to different distributions. 4) Generic. Furthermore, LDA can adapt to unseen distribution by utilizing very few training data without re-training. Extensive experiments demonstrate that our framework can 1) make the final representation space both intra-class compact and inter-class separable, 2) outperform the state-of-the-art methods on multiple standard FAS benchmarks.

Abstract: It is well known that computer vision can be unreliable when faced with previously unseen imaging conditions. This paper proposes a method to adapt camera parameters according to a normalizing flow-based out-of-distibution detector. A small-scale study is conducted which shows that adapting camera parameters according to this out-of-distibution detector leads to an average increase of 3 to 4 percentage points in mAP, mAR and F1 performance metrics of a YOLOv4 object detector. As a secondary result, this paper also shows that it is possible to train a normalizing flow model for out-of-distribution detection on the COCO dataset, which is larger and more diverse than most benchmarks for out-of-distibution detectors.

Abstract: Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks. However, traditional aggregation-based multimodal fusion methods ignore the inter-modality relationship, treat each modality equally, suffer sensor noise, and thus reduce multimodal learning performance. In this work, we propose a novel multimodal contrastive method to explore more reliable multimodal representations under the weak supervision of unimodal predicting. Specifically, we first capture task-related unimodal representations and the unimodal predictions from the introduced unimodal predicting task. Then the unimodal representations are aligned with the more effective one by the designed multimodal contrastive method under the supervision of the unimodal predictions. Experimental results with fused features on two image-text classification benchmarks UPMC-Food-101 and N24News show that our proposed Unimodality-Supervised MultiModal Contrastive UniS-MMC learning method outperforms current state-of-the-art multimodal methods. The detailed ablation study and analysis further demonstrate the advantage of our proposed method.

Abstract: We introduce a novel dataset consisting of images depicting pink eggs that have been identified as Pomacea canaliculata eggs, accompanied by corresponding bounding box annotations. The purpose of this dataset is to aid researchers in the analysis of the spread of Pomacea canaliculata species by utilizing deep learning techniques, as well as supporting other investigative pursuits that require visual data pertaining to the eggs of Pomacea canaliculata. It is worth noting, however, that the identity of the eggs in question is not definitively established, as other species within the same taxonomic family have been observed to lay similar-looking eggs in regions of the Americas. Therefore, a crucial prerequisite to any decision regarding the elimination of these eggs would be to establish with certainty whether they are exclusively attributable to invasive Pomacea canaliculata or if other species are also involved. The dataset is available at https://www.kaggle.com/datasets/deeshenzhen/pinkeggs

Abstract: Since adversarial examples appeared and showed the catastrophic degradation they brought to DNN, many adversarial defense methods have been devised, among which adversarial training is considered the most effective. However, a recent work showed the inequality phenomena in $l_{\infty}$-adversarial training and revealed that the $l_{\infty}$-adversarially trained model is vulnerable when a few important pixels are perturbed by i.i.d. noise or occluded. In this paper, we propose a simple yet effective method called Input Gradient Distillation to release the inequality phenomena in $l_{\infty}$-adversarial training. Experiments show that while preserving the model's adversarial robustness, Input Gradient Distillation improves the model's robustness to i.i.d. noise and occlusion. Moreover, we formally explain why the equality of the model's saliency map can improve the model's robustness to i.i.d. noise or occlusion. Github:https://github.com/fhdnskfbeuv/Inuput-Gradient-Distillation

Abstract: Multi-modal visual understanding of images with prompts involves using various visual and textual cues to enhance the semantic understanding of images. This approach combines both vision and language processing to generate more accurate predictions and recognition of images. By utilizing prompt-based techniques, models can learn to focus on certain features of an image to extract useful information for downstream tasks. Additionally, multi-modal understanding can improve upon single modality models by providing more robust representations of images. Overall, the combination of visual and textual information is a promising area of research for advancing image recognition and understanding. In this paper we will try an amount of prompt design methods and propose a new method for better extraction of semantic information

Abstract: Image quality assessment is a fundamental problem in the field of image processing, and due to the lack of reference images in most practical scenarios, no-reference image quality assessment (NR-IQA), has gained increasing attention recently. With the development of deep learning technology, many deep neural network-based NR-IQA methods have been developed, which try to learn the image quality based on the understanding of database information. Currently, Transformer has achieved remarkable progress in various vision tasks. Since the characteristics of the attention mechanism in Transformer fit the global perceptual impact of artifacts perceived by a human, Transformer is thus well suited for image quality assessment tasks. In this paper, we propose a Transformer based NR-IQA model using a predicted objective error map and perceptual quality token. Specifically, we firstly generate the predicted error map by pre-training one model consisting of a Transformer encoder and decoder, in which the objective difference between the distorted and the reference images is used as supervision. Then, we freeze the parameters of the pre-trained model and design another branch using the vision Transformer to extract the perceptual quality token for feature fusion with the predicted error map. Finally, the fused features are regressed to the final image quality score. Extensive experiments have shown that our proposed method outperforms the current state-of-the-art in both authentic and synthetic image databases. Moreover, the attentional map extracted by the perceptual quality token also does conform to the characteristics of the human visual system.

Abstract: As people's aesthetic preferences for images are far from understood, image aesthetic assessment is a challenging artificial intelligence task. The range of factors underlying this task is almost unlimited, but we know that some aesthetic attributes affect those preferences. In this study, we present a multi-task convolutional neural network that takes into account these attributes. The proposed neural network jointly learns the attributes along with the overall aesthetic scores of images. This multi-task learning framework allows for effective generalization through the utilization of shared representations. Our experiments demonstrate that the proposed method outperforms the state-of-the-art approaches in predicting overall aesthetic scores for images in one benchmark of image aesthetics. We achieve near-human performance in terms of overall aesthetic scores when considering the Spearman's rank correlations. Moreover, our model pioneers the application of multi-tasking in another benchmark, serving as a new baseline for future research. Notably, our approach achieves this performance while using fewer parameters compared to existing multi-task neural networks in the literature, and consequently makes our method more efficient in terms of computational complexity.

Abstract: Presentation attack is a challenging issue that persists in the security of automatic fingerprint recognition systems. This paper proposes a novel explainable residual slim network that detects the presentation attack by representing the visual features in the input fingerprint sample. The encoder-decoder of this network along with the channel attention block converts the input sample into its heatmap representation while the modified residual convolutional neural network classifier discriminates between live and spoof fingerprints. The entire architecture of the heatmap generator block and modified ResNet classifier works together in an end-to-end manner. The performance of the proposed model is validated on benchmark liveness detection competition databases i.e. Livdet 2011, 2013, 2015, 2017, and 2019 and the classification accuracy of 96.86\%, 99.84\%, 96.45\%, 96.07\%, 96.27\% are achieved on them, respectively. The performance of the proposed model is compared with the state-of-the-art techniques, and the proposed method outperforms state-of-the-art methods in benchmark protocols of presentation attack detection in terms of classification accuracy.

Abstract: We propose a method that augments a simulated dataset using diffusion models to improve the performance of pedestrian detection in real-world data. The high cost of collecting and annotating data in the real-world has motivated the use of simulation platforms to create training datasets. While simulated data is inexpensive to collect and annotate, it unfortunately does not always closely match the distribution of real-world data, which is known as the sim2real gap. In this paper we propose a novel method of synthetic data creation meant to close the sim2real gap for the challenging pedestrian detection task. Our method uses a diffusion-based architecture to learn a real-world distribution which, once trained, is used to generate datasets. We mix this generated data with simulated data as a form of augmentation and show that training on a combination of generated and simulated data increases average precision by as much as 27.3% for pedestrian detection models in real-world data, compared against training on purely simulated data.

Abstract: Visual quality inspection in high performance manufacturing can benefit from automation, due to cost savings and improved rigor. Deep learning techniques are the current state of the art for generic computer vision tasks like classification and object detection. Manufacturing data can pose a challenge for deep learning because data is highly repetitive and there are few images of defects or deviations to learn from. Deep learning models trained with such data can be fragile and sensitive to context, and can under-detect new defects not found in the training data. In this work, we explore training defect detection models to learn specific defects out of context, so that they are more likely to be detected in new situations. We demonstrate how models trained on diverse images containing a common defect type can pick defects out in new circumstances. Such generic models could be more robust to new defects not found data collected for training, and can reduce data collection impediments to implementing visual inspection on production lines. Additionally, we demonstrate that object detection models trained to predict a label and bounding box outperform classifiers that predict a label only on held out test data typical of manufacturing inspection tasks. Finally, we studied the factors that affect generalization in order to train models that work under a wider range of conditions.

Abstract: Segment Anything Model (SAM) is a new foundation model that can be used as a zero-shot object segmentation method with the use of either guide prompts such as bounding boxes, polygons, or points. Alternatively, additional post processing steps can be used to identify objects of interest after segmenting everything in an image. Here we present a method using segment anything together with a series of post processing steps to segment potato leaves, called Leaf Only SAM. The advantage of this proposed method is that it does not require any training data to produce its results so has many applications across the field of plant phenotyping where there is limited high quality annotated data available. We compare the performance of Leaf Only SAM to a Mask R-CNN model which has been fine-tuned on our small novel potato leaf dataset. On the evaluation dataset, Leaf Only SAM finds an average recall of 63.2 and an average precision of 60.3, compared to recall of 78.7 and precision of 74.7 for Mask R-CNN. Leaf Only SAM does not perform better than the fine-tuned Mask R-CNN model on our data, but the SAM based model does not require any extra training or annotation of our new dataset. This shows there is potential to use SAM as a zero-shot classifier with the addition of post processing steps.

Abstract: Medical image segmentation is a critical step in computer-aided diagnosis, and convolutional neural networks are popular segmentation networks nowadays. However, the inherent local operation characteristics make it difficult to focus on the global contextual information of lesions with different positions, shapes, and sizes. Semi-supervised learning can be used to learn from both labeled and unlabeled samples, alleviating the burden of manual labeling. However, obtaining a large number of unlabeled images in medical scenarios remains challenging. To address these issues, we propose a Multi-level Global Context Cross-consistency (MGCC) framework that uses images generated by a Latent Diffusion Model (LDM) as unlabeled images for semi-supervised learning. The framework involves of two stages. In the first stage, a LDM is used to generate synthetic medical images, which reduces the workload of data annotation and addresses privacy concerns associated with collecting medical data. In the second stage, varying levels of global context noise perturbation are added to the input of the auxiliary decoder, and output consistency is maintained between decoders to improve the representation ability. Experiments conducted on open-source breast ultrasound and private thyroid ultrasound datasets demonstrate the effectiveness of our framework in bridging the probability distribution and the semantic representation of the medical image. Our approach enables the effective transfer of probability distribution knowledge to the segmentation network, resulting in improved segmentation accuracy. The code is available at https://github.com/FengheTan9/Multi-Level Global-Context-Cross-Consistency.

Abstract: Many convolutional neural networks (CNNs) rely on progressive downsampling of their feature maps to increase the network's receptive field and decrease computational cost. However, this comes at the price of losing granularity in the feature maps, limiting the ability to correctly understand images or recover fine detail in dense prediction tasks. To address this, common practice is to replace the last few downsampling operations in a CNN with dilated convolutions, allowing to retain the feature map resolution without reducing the receptive field, albeit increasing the computational cost. This allows to trade off predictive performance against cost, depending on the output feature resolution. By either regularly downsampling or not downsampling the entire feature map, existing work implicitly treats all regions of the input image and subsequent feature maps as equally important, which generally does not hold. We propose an adaptive downsampling scheme that generalizes the above idea by allowing to process informative regions at a higher resolution than less informative ones. In a variety of experiments, we demonstrate the versatility of our adaptive downsampling strategy and empirically show that it improves the cost-accuracy trade-off of various established CNNs.

Abstract: Recently, Users Generated Content (UGC) videos becomes ubiquitous in our daily lives. However, due to the limitations of photographic equipments and techniques, UGC videos often contain various degradations, in which one of the most visually unfavorable effects is the underexposure. Therefore, corresponding video enhancement algorithms such as Low-Light Video Enhancement (LLVE) have been proposed to deal with the specific degradation. However, different from video enhancement algorithms, almost all existing Video Quality Assessment (VQA) models are built generally rather than specifically, which measure the quality of a video from a comprehensive perspective. To the best of our knowledge, there is no VQA model specially designed for videos enhanced by LLVE algorithms. To this end, we first construct a Low-Light Video Enhancement Quality Assessment (LLVE-QA) dataset in which 254 original low-light videos are collected and then enhanced by leveraging 8 LLVE algorithms to obtain 2,060 videos in total. Moreover, we propose a quality assessment model specialized in LLVE, named Light-VQA. More concretely, since the brightness and noise have the most impact on low-light enhanced VQA, we handcraft corresponding features and integrate them with deep-learning-based semantic features as the overall spatial information. As for temporal information, in addition to deep-learning-based motion features, we also investigate the handcrafted brightness consistency among video frames, and the overall temporal information is their concatenation. Subsequently, spatial and temporal information is fused to obtain the quality-aware representation of a video. Extensive experimental results show that our Light-VQA achieves the best performance against the current State-Of-The-Art (SOTA) on LLVE-QA and public dataset. Dataset and Codes can be found at https://github.com/wenzhouyidu/Light-VQA.

Abstract: Detection-based tracking is one of the main methods of multi-object tracking. It can obtain good tracking results when using excellent detectors but it may associate wrong targets when facing overlapping and low-confidence detections. To address this issue, this paper proposes a multi-object tracker based on shape constraint and confidence named SCTracker. In the data association stage, an Intersection of Union distance with shape constraints is applied to calculate the cost matrix between tracks and detections, which can effectively avoid the track tracking to the wrong target with the similar position but inconsistent shape, so as to improve the accuracy of data association. Additionally, the Kalman Filter based on the detection confidence is used to update the motion state to improve the tracking performance when the detection has low confidence. Experimental results on MOT 17 dataset show that the proposed method can effectively improve the tracking performance of multi-object tracking.

Abstract: We propose a differentiable nonlinear least squares framework to account for uncertainty in relative pose estimation from feature correspondences. Specifically, we introduce a symmetric version of the probabilistic normal epipolar constraint, and an approach to estimate the covariance of feature positions by differentiating through the camera pose estimation procedure. We evaluate our approach on synthetic, as well as the KITTI and EuRoC real-world datasets. On the synthetic dataset, we confirm that our learned covariances accurately approximate the true noise distribution. In real world experiments, we find that our approach consistently outperforms state-of-the-art non-probabilistic and probabilistic approaches, regardless of the feature extraction algorithm of choice.

Abstract: Nighttime image dehazing is a challenging task due to the presence of multiple types of adverse degrading effects including glow, haze, blurry, noise, color distortion, and so on. However, most previous studies mainly focus on daytime image dehazing or partial degradations presented in nighttime hazy scenes, which may lead to unsatisfactory restoration results. In this paper, we propose an end-to-end transformer-based framework for nighttime haze removal, called NightHazeFormer. Our proposed approach consists of two stages: supervised pre-training and semi-supervised fine-tuning. During the pre-training stage, we introduce two powerful priors into the transformer decoder to generate the non-learnable prior queries, which guide the model to extract specific degradations. For the fine-tuning, we combine the generated pseudo ground truths with input real-world nighttime hazy images as paired images and feed into the synthetic domain to fine-tune the pre-trained model. This semi-supervised fine-tuning paradigm helps improve the generalization to real domain. In addition, we also propose a large-scale synthetic dataset called UNREAL-NH, to simulate the real-world nighttime haze scenarios comprehensively. Extensive experiments on several synthetic and real-world datasets demonstrate the superiority of our NightHazeFormer over state-of-the-art nighttime haze removal methods in terms of both visually and quantitatively.

Abstract: Action recognition is an important problem that requires identifying actions in video by learning complex interactions across scene actors and objects. However, modern deep-learning based networks often require significant computation, and may capture scene context using various modalities that further increases compute costs. Efficient methods such as those used for AR/VR often only use human-keypoint information but suffer from a loss of scene context that hurts accuracy. In this paper, we describe an action-localization method, KeyNet, that uses only the keypoint data for tracking and action recognition. Specifically, KeyNet introduces the use of object based keypoint information to capture context in the scene. Our method illustrates how to build a structured intermediate representation that allows modeling higher-order interactions in the scene from object and human keypoints without using any RGB information. We find that KeyNet is able to track and classify human actions at just 5 FPS. More importantly, we demonstrate that object keypoints can be modeled to recover any loss in context from using keypoint information over AVA action and Kinetics datasets.

Abstract: Deep learning implemented with convolutional network architectures can exceed specialists' diagnostic accuracy. However, whole-image deep learning trained on a given dataset may not generalize to other datasets. The problem arises because extra-lesional features - ruler marks, ink marks, and other melanoma correlates - may serve as information leaks. These extra-lesional features, discoverable by heat maps, degrade melanoma diagnostic performance and cause techniques learned on one data set to fail to generalize. We propose a novel technique to improve melanoma recognition by an EfficientNet model. The model trains the network to detect the lesion and learn features from the detected lesion. A generalizable elliptical segmentation model for lesions was developed, with an ellipse enclosing a lesion and the ellipse enclosed by an extended rectangle (bounding box). The minimal bounding box was extended by 20% to allow some background around the lesion. The publicly available International Skin Imaging Collaboration (ISIC) 2020 skin lesion image dataset was used to evaluate the effectiveness of the proposed method. Our test results show that the proposed method improved diagnostic accuracy by increasing the mean area under receiver operating characteristic curve (mean AUC) score from 0.9 to 0.922. Additionally, correctly diagnosed scores are also improved, providing better separation of scores, thereby increasing melanoma diagnostic confidence. The proposed lesion-focused convolutional technique warrants further study.

Abstract: This paper presents a pixel selection method for compact image representation based on superpixel segmentation and tensor completion. Our method divides the image into several regions that capture important textures or semantics and selects a representative pixel from each region to store. We experiment with different criteria for choosing the representative pixel and find that the centroid pixel performs the best. We also propose two smooth tensor completion algorithms that can effectively reconstruct different types of images from the selected pixels. Our experiments show that our superpixel-based method achieves better results than uniform sampling for various missing ratios.

Abstract: In this paper we propose the Ray-Patch decoder, a novel model to efficiently query transformers to decode implicit representations into target views. Our Ray-Patch decoding reduces the computational footprint up to two orders of magnitude compared to previous models, without losing global attention, and hence maintaining specific task metrics. The key idea of our novel decoder is to split the target image into a set of patches, then querying the transformer for each patch to extract a set of feature vectors, which are finally decoded into the target image using convolutional layers. Our experimental results quantify the effectiveness of our method, specifically the notable boost in rendering speed and equal specific task metrics for different baselines and datasets.

Abstract: Moving Object Segmentation (MOS) is a challenging problem in computer vision, particularly in scenarios with dynamic backgrounds, abrupt lighting changes, shadows, camouflage, and moving cameras. While graph-based methods have shown promising results in MOS, they have mainly relied on transductive learning which assumes access to the entire training and testing data for evaluation. However, this assumption is not realistic in real-world applications where the system needs to handle new data during deployment. In this paper, we propose a novel Graph Inductive Moving Object Segmentation (GraphIMOS) algorithm based on a Graph Neural Network (GNN) architecture. Our approach builds a generic model capable of performing prediction on newly added data frames using the already trained model. GraphIMOS outperforms previous inductive learning methods and is more generic than previous transductive techniques. Our proposed algorithm enables the deployment of graph-based MOS models in real-world applications.

Abstract: A promise of Generative Adversarial Networks (GANs) is to provide cheap photorealistic data for training and validating AI models in autonomous driving. Despite their huge success, their performance on complex images featuring multiple objects is understudied. While some frameworks produce high-quality street scenes with little to no control over the image content, others offer more control at the expense of high-quality generation. A common limitation of both approaches is the use of global latent codes for the whole image, which hinders the learning of independent object distributions. Motivated by SemanticStyleGAN (SSG), a recent work on latent space disentanglement in human face generation, we propose a novel framework, Urban-StyleGAN, for urban scene generation and manipulation. We find that a straightforward application of SSG leads to poor results because urban scenes are more complex than human faces. To provide a more compact yet disentangled latent representation, we develop a class grouping strategy wherein individual classes are grouped into super-classes. Moreover, we employ an unsupervised latent exploration algorithm in the $\mathcal{S}$-space of the generator and show that it is more efficient than the conventional $\mathcal{W}^{+}$-space in controlling the image content. Results on the Cityscapes and Mapillary datasets show the proposed approach achieves significantly more controllability and improved image quality than previous approaches on urban scenes and is on par with general-purpose non-controllable generative models (like StyleGAN2) in terms of quality.

Abstract: Recent semantic segmentation models accurately classify test-time examples that are similar to a training dataset distribution. However, their discriminative closed-set approach is not robust in practical data setups with distributional shifts and out-of-distribution (OOD) classes. As a result, the predicted probabilities can be very imprecise when used as confidence scores at test time. To address this, we propose a generative model for concurrent in-distribution misclassification (IDM) and OOD detection that relies on a normalizing flow framework. The proposed flow-based detector with an energy-based inputs (FlowEneDet) can extend previously deployed segmentation models without their time-consuming retraining. Our FlowEneDet results in a low-complexity architecture with marginal increase in the memory footprint. FlowEneDet achieves promising results on Cityscapes, Cityscapes-C, FishyScapes and SegmentMeIfYouCan benchmarks in IDM/OOD detection when applied to pretrained DeepLabV3+ and SegFormer semantic segmentation models.

Abstract: In this paper, we introduce FitMe, a facial reflectance model and a differentiable rendering optimization pipeline, that can be used to acquire high-fidelity renderable human avatars from single or multiple images. The model consists of a multi-modal style-based generator, that captures facial appearance in terms of diffuse and specular reflectance, and a PCA-based shape model. We employ a fast differentiable rendering process that can be used in an optimization pipeline, while also achieving photorealistic facial shading. Our optimization process accurately captures both the facial reflectance and shape in high-detail, by exploiting the expressivity of the style-based latent representation and of our shape model. FitMe achieves state-of-the-art reflectance acquisition and identity preservation on single "in-the-wild" facial images, while it produces impressive scan-like results, when given multiple unconstrained facial images pertaining to the same identity. In contrast with recent implicit avatar reconstructions, FitMe requires only one minute and produces relightable mesh and texture-based avatars, that can be used by end-user applications.

Abstract: Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a semantic layout is used to generate a photorealistic image. State-of-the-art conditional Generative Adversarial Networks (GANs) need a huge amount of paired data to accomplish this task while generic unpaired image-to-image translation frameworks underperform in comparison, because they color-code semantic layouts and learn correspondences in appearance instead of semantic content. Starting from the assumption that a high quality generated image should be segmented back to its semantic layout, we propose a new Unsupervised paradigm for SIS (USIS) that makes use of a self-supervised segmentation loss and whole image wavelet based discrimination. Furthermore, in order to match the high-frequency distribution of real images, a novel generator architecture in the wavelet domain is proposed. We test our methodology on 3 challenging datasets and demonstrate its ability to bridge the performance gap between paired and unpaired models.

Abstract: Text-guided human motion generation has drawn significant interest because of its impactful applications spanning animation and robotics. Recently, application of diffusion models for motion generation has enabled improvements in the quality of generated motions. However, existing approaches are limited by their reliance on relatively small-scale motion capture data, leading to poor performance on more diverse, in-the-wild prompts. In this paper, we introduce Make-An-Animation, a text-conditioned human motion generation model which learns more diverse poses and prompts from large-scale image-text datasets, enabling significant improvement in performance over prior works. Make-An-Animation is trained in two stages. First, we train on a curated large-scale dataset of (text, static pseudo-pose) pairs extracted from image-text datasets. Second, we fine-tune on motion capture data, adding additional layers to model the temporal dimension. Unlike prior diffusion models for motion generation, Make-An-Animation uses a U-Net architecture similar to recent text-to-video generation models. Human evaluation of motion realism and alignment with input text shows that our model reaches state-of-the-art performance on text-to-motion generation.

Abstract: Humans can easily understand a single image as depicting multiple potential objects permitting interaction. We use this skill to plan our interactions with the world and accelerate understanding new objects without engaging in interaction. In this paper, we would like to endow machines with the similar ability, so that intelligent agents can better explore the 3D scene or manipulate objects. Our approach is a transformer-based model that predicts the 3D location, physical properties and affordance of objects. To power this model, we collect a dataset with Internet videos, egocentric videos and indoor images to train and validate our approach. Our model yields strong performance on our data, and generalizes well to robotics data.