Computer Vision and Pattern Recognition (cs.CV)

Abstract: Large-scale pre-trained models have been remarkably successful in resolving downstream tasks. Nonetheless, deploying these models on low-capability devices still requires an effective approach, such as model pruning. However, pruning the model from scratch can pose a practical challenge given the limited resources of each downstream task or device. To tackle this issue, we present a scalable one-shot pruning method that leverages pruned knowledge of similar tasks to extract a sub-network from the pre-trained model for a new task. Specifically, we create a score mask using the pruned models of similar tasks to identify task-specific filters/nodes in the pre-trained model for the new task. Based on this mask, we conduct a single round of pruning to extract a suitably-sized sub-network that can quickly adapt to the new task with only a few training iterations. Our experimental analysis demonstrates the effectiveness of the proposed method on the convolutional neural networks (CNNs) and vision transformers (ViT) with various datasets. The proposed method consistently outperforms popular pruning baseline methods in terms of accuracy and efficiency when dealing with diverse downstream tasks with different memory constraints.

Abstract: Diabetic Retinopathy (DR) is a common complication of diabetes and a leading cause of blindness worldwide. Early and accurate grading of its severity is crucial for disease management. Although deep learning has shown great potential for automated DR grading, its real-world deployment is still challenging due to distribution shifts among source and target domains, known as the domain generalization problem. Existing works have mainly attributed the performance degradation to limited domain shifts caused by simple visual discrepancies, which cannot handle complex real-world scenarios. Instead, we present preliminary evidence suggesting the existence of three-fold generalization issues: visual and degradation style shifts, diagnostic pattern diversity, and data imbalance. To tackle these issues, we propose a novel unified framework named Generalizable Diabetic Retinopathy Grading Network (GDRNet). GDRNet consists of three vital components: fundus visual-artifact augmentation (FundusAug), dynamic hybrid-supervised loss (DahLoss), and domain-class-aware re-balancing (DCR). FundusAug generates realistic augmented images via visual transformation and image degradation, while DahLoss jointly leverages pixel-level consistency and image-level semantics to capture the diverse diagnostic patterns and build generalizable feature representations. Moreover, DCR mitigates the data imbalance from a domain-class view and avoids undesired over-emphasis on rare domain-class pairs. Finally, we design a publicly available benchmark for fair evaluations. Extensive comparison experiments against advanced methods and exhaustive ablation studies demonstrate the effectiveness and generalization ability of GDRNet.

Abstract: Segmentation of objects in a video is challenging due to the nuances such as motion blurring, parallax, occlusions, changes in illumination, etc. Instead of addressing these nuances separately, we focus on building a generalizable solution that avoids overfitting to the individual intricacies. Such a solution would also help us save enormous resources involved in human annotation of video corpora. To solve Video Object Segmentation (VOS) in an unsupervised setting, we propose a new pipeline (FODVid) based on the idea of guiding segmentation outputs using flow-guided graph-cut and temporal consistency. Basically, we design a segmentation model incorporating intra-frame appearance and flow similarities, and inter-frame temporal continuation of the objects under consideration. We perform an extensive experimental analysis of our straightforward methodology on the standard DAVIS16 video benchmark. Though simple, our approach produces results comparable (within a range of ~2 mIoU) to the existing top approaches in unsupervised VOS. The simplicity and effectiveness of our technique opens up new avenues for research in the video domain.

Abstract: The Global Precedence Effect (GPE) suggests that the processing of global properties of a visual stimulus precedes the processing of local properties. The generality of this theory was argued for four decades during different known Perceptual Field Variables. The effect size of various PFVs, regarding the findings during these four decades, were pooled in our recent meta-analysis study. Pursuing the study, in the present paper, we explore the effects of Congruency, Size, and Sparsity and their interaction on global advantage in two different experiments with different task paradigms; Matching judgment and Similarity judgment. Upon results of these experiments, Congruency and Size have significant effects and Sparsity has small effects. Also, the task paradigm and its interaction with other PFVs are shown significant effects in this study, which shows the prominence of the role of task paradigms in evaluating PFVs' effects on GPE. Also, we found that the effects of these parameters were not specific to the special condition that individuals were instructed to retinal stabilize. So, the experiments were more extendible to daily human behavior.

Abstract: Knee osteoarthritis (KOA) is a widespread condition that can cause chronic pain and stiffness in the knee joint. Early detection and diagnosis are crucial for successful clinical intervention and management to prevent severe complications, such as loss of mobility. In this paper, we propose an automated approach that employs the Swin Transformer to predict the severity of KOA. Our model uses publicly available radiographic datasets with Kellgren and Lawrence scores to enable early detection and severity assessment. To improve the accuracy of our model, we employ a multi-prediction head architecture that utilizes multi-layer perceptron classifiers. Additionally, we introduce a novel training approach that reduces the data drift between multiple datasets to ensure the generalization ability of the model. The results of our experiments demonstrate the effectiveness and feasibility of our approach in predicting KOA severity accurately.

Abstract: Edge computing aims to enable edge devices, such as IoT devices, to process data locally instead of relying on the cloud. However, deep learning techniques like computer vision and natural language processing can be computationally expensive and memory-intensive. Creating manual architectures specialized for each device is infeasible due to their varying memory and computational constraints. To address these concerns, we automate the construction of task-specific deep learning architectures optimized for device constraints through Neural Architecture Search (NAS). We present DCA-NAS, a principled method of fast neural network architecture search that incorporates edge-device constraints such as model size and floating-point operations. It incorporates weight sharing and channel bottleneck techniques to speed up the search time. Based on our experiments, we see that DCA-NAS outperforms manual architectures for similar sized models and is comparable to popular mobile architectures on various image classification datasets like CIFAR-10, CIFAR-100, and Imagenet-1k. Experiments with search spaces -- DARTS and NAS-Bench-201 show the generalization capabilities of DCA-NAS. On further evaluating our approach on Hardware-NAS-Bench, device-specific architectures with low inference latency and state-of-the-art performance were discovered.

Abstract: Image Quality Assessment (IQA) is a challenging task that requires training on massive datasets to achieve accurate predictions. However, due to the lack of IQA data, deep learning-based IQA methods typically rely on pre-trained networks trained on massive datasets as feature extractors to enhance their generalization ability, such as the ResNet network trained on ImageNet. In this paper, we utilize the encoder of Segment Anything, a recently proposed segmentation model trained on a massive dataset, for high-level semantic feature extraction. Most IQA methods are limited to extracting spatial-domain features, while frequency-domain features have been shown to better represent noise and blur. Therefore, we leverage both spatial-domain and frequency-domain features by applying Fourier and standard convolutions on the extracted features, respectively. Extensive experiments are conducted to demonstrate the effectiveness of all the proposed components, and results show that our approach outperforms the state-of-the-art (SOTA) in four representative datasets, both qualitatively and quantitatively. Our experiments confirm the powerful feature extraction capabilities of Segment Anything and highlight the value of combining spatial-domain and frequency-domain features in IQA tasks. Code: https://github.com/Hedlen/SAM-IQA

Abstract: The ability to scene understanding in adverse visual conditions, e.g., nighttime, has sparked active research for RGB-Thermal (RGB-T) semantic segmentation. However, it is essentially hampered by two critical problems: 1) the day-night gap of RGB images is larger than that of thermal images, and 2) the class-wise performance of RGB images at night is not consistently higher or lower than that of thermal images. we propose the first test-time adaptation (TTA) framework, dubbed Night-TTA, to address the problems for nighttime RGBT semantic segmentation without access to the source (daytime) data during adaptation. Our method enjoys three key technical parts. Firstly, as one modality (e.g., RGB) suffers from a larger domain gap than that of the other (e.g., thermal), Imaging Heterogeneity Refinement (IHR) employs an interaction branch on the basis of RGB and thermal branches to prevent cross-modal discrepancy and performance degradation. Then, Class Aware Refinement (CAR) is introduced to obtain reliable ensemble logits based on pixel-level distribution aggregation of the three branches. In addition, we also design a specific learning scheme for our TTA framework, which enables the ensemble logits and three student logits to collaboratively learn to improve the quality of predictions during the testing phase of our Night TTA. Extensive experiments show that our method achieves state-of-the-art (SoTA) performance with a 13.07% boost in mIoU.

Abstract: Coronary artery segmentation on coronary-computed tomography angiography (CCTA) images is crucial for clinical use. Due to the expertise-required and labor-intensive annotation process, there is a growing demand for the relevant label-efficient learning algorithms. To this end, we propose partial vessels annotation (PVA) based on the challenges of coronary artery segmentation and clinical diagnostic characteristics. Further, we propose a progressive weakly supervised learning framework to achieve accurate segmentation under PVA. First, our proposed framework learns the local features of vessels to propagate the knowledge to unlabeled regions. Subsequently, it learns the global structure by utilizing the propagated knowledge, and corrects the errors introduced in the propagation process. Finally, it leverages the similarity between feature embeddings and the feature prototype to enhance testing outputs. Experiments on clinical data reveals that our proposed framework outperforms the competing methods under PVA (24.29% vessels), and achieves comparable performance in trunk continuity with the baseline model using full annotation (100% vessels).

Abstract: Wearable sensors such as Inertial Measurement Units (IMUs) are often used to assess the performance of human exercise. Common approaches use handcrafted features based on domain expertise or automatically extracted features using time series analysis. Multiple sensors are required to achieve high classification accuracy, which is not very practical. These sensors require calibration and synchronization and may lead to discomfort over longer time periods. Recent work utilizing computer vision techniques has shown similar performance using video, without the need for manual feature engineering, and avoiding some pitfalls such as sensor calibration and placement on the body. In this paper, we compare the performance of IMUs to a video-based approach for human exercise classification on two real-world datasets consisting of Military Press and Rowing exercises. We compare the performance using a single camera that captures video in the frontal view versus using 5 IMUs placed on different parts of the body. We observe that an approach based on a single camera can outperform a single IMU by 10 percentage points on average. Additionally, a minimum of 3 IMUs are required to outperform a single camera. We observe that working with the raw data using multivariate time series classifiers outperforms traditional approaches based on handcrafted or automatically extracted features. Finally, we show that an ensemble model combining the data from a single camera with a single IMU outperforms either data modality. Our work opens up new and more realistic avenues for this application, where a video captured using a readily available smartphone camera, combined with a single sensor, can be used for effective human exercise classification.

Abstract: SfM (Structure from Motion) has been extensively used for UAV (Unmanned Aerial Vehicle) image orientation. Its efficiency is directly influenced by feature matching. Although image retrieval has been extensively used for match pair selection, high computational costs are consumed due to a large number of local features and the large size of the used codebook. Thus, this paper proposes an efficient match pair retrieval method and implements an integrated workflow for parallel SfM reconstruction. First, an individual codebook is trained online by considering the redundancy of UAV images and local features, which avoids the ambiguity of training codebooks from other datasets. Second, local features of each image are aggregated into a single high-dimension global descriptor through the VLAD (Vector of Locally Aggregated Descriptors) aggregation by using the trained codebook, which remarkably reduces the number of features and the burden of nearest neighbor searching in image indexing. Third, the global descriptors are indexed via the HNSW (Hierarchical Navigable Small World) based graph structure for the nearest neighbor searching. Match pairs are then retrieved by using an adaptive threshold selection strategy and utilized to create a view graph for divide-and-conquer based parallel SfM reconstruction. Finally, the performance of the proposed solution has been verified using three large-scale UAV datasets. The test results demonstrate that the proposed solution accelerates match pair retrieval with a speedup ratio ranging from 36 to 108 and improves the efficiency of SfM reconstruction with competitive accuracy in both relative and absolute orientation.

Abstract: The ability to detect learned objects regardless of their appearance is crucial for autonomous systems in real-world applications. Especially for detecting humans, which is often a fundamental task in safety-critical applications, it is vital to prevent errors. To address this challenge, we propose a self-monitoring framework that allows for the perception system to perform plausibility checks at runtime. We show that by incorporating an additional component for detecting human body parts, we are able to significantly reduce the number of missed human detections by factors of up to 9 when compared to a baseline setup, which was trained only on holistic person objects. Additionally, we found that training a model jointly on humans and their body parts leads to a substantial reduction in false positive detections by up to 50% compared to training on humans alone. We performed comprehensive experiments on the publicly available datasets DensePose and Pascal VOC in order to demonstrate the effectiveness of our framework. Code is available at https://github.com/ FraunhoferIKS/smf-object-detection.

Abstract: In this work, we present an efficient and quantization-aware panoptic driving perception model (Q- YOLOP) for object detection, drivable area segmentation, and lane line segmentation, in the context of autonomous driving. Our model employs the Efficient Layer Aggregation Network (ELAN) as its backbone and task-specific heads for each task. We employ a four-stage training process that includes pretraining on the BDD100K dataset, finetuning on both the BDD100K and iVS datasets, and quantization-aware training (QAT) on BDD100K. During the training process, we use powerful data augmentation techniques, such as random perspective and mosaic, and train the model on a combination of the BDD100K and iVS datasets. Both strategies enhance the model's generalization capabilities. The proposed model achieves state-of-the-art performance with an [email protected] of 0.622 for object detection and an mIoU of 0.612 for segmentation, while maintaining low computational and memory requirements.

Abstract: Fueled by deep learning, computer-aided diagnosis achieves huge advances. However, out of controlled lab environments, algorithms could face multiple challenges. Open set recognition (OSR), as an important one, states that categories unseen in training could appear in testing. In medical fields, it could derive from incompletely collected training datasets and the constantly emerging new or rare diseases. OSR requires an algorithm to not only correctly classify known classes, but also recognize unknown classes and forward them to experts for further diagnosis. To tackle OSR, we assume that known classes could densely occupy small parts of the embedding space and the remaining sparse regions could be recognized as unknowns. Following it, we propose Open Margin Cosine Loss (OMCL) unifying two mechanisms. The former, called Margin Loss with Adaptive Scale (MLAS), introduces angular margin for reinforcing intra-class compactness and inter-class separability, together with an adaptive scaling factor to strengthen the generalization capacity. The latter, called Open-Space Suppression (OSS), opens the classifier by recognizing sparse embedding space as unknowns using proposed feature space descriptors. Besides, since medical OSR is still a nascent field, two publicly available benchmark datasets are proposed for comparison. Extensive ablation studies and feature visualization demonstrate the effectiveness of each design. Compared with state-of-the-art methods, MLAS achieves superior performances, measured by ACC, AUROC, and OSCR.

Abstract: Data-free knowledge distillation (DFKD) aims to obtain a lightweight student model without original training data. Existing works generally synthesize data from the pre-trained teacher model to replace the original training data for student learning. To more effectively train the student model, the synthetic data shall be customized to the current student learning ability. However, this is ignored in the existing DFKD methods and thus negatively affects the student training. To address this issue, we propose Customizing Synthetic Data for Data-Free Student Learning (CSD) in this paper, which achieves adaptive data synthesis using a self-supervised augmented auxiliary task to estimate the student learning ability. Specifically, data synthesis is dynamically adjusted to enlarge the cross entropy between the labels and the predictions from the self-supervised augmented task, thus generating hard samples for the student model. The experiments on various datasets and teacher-student models show the effectiveness of our proposed method. Code is available at: $\href{https://github.com/luoshiya/CSD}{https://github.com/luoshiya/CSD}$

Abstract: Recent advances in deep neural networks have achieved unprecedented success in visual speech recognition. However, there remains substantial disparity between current methods and their deployment in resource-constrained devices. In this work, we explore different magnitude-based pruning techniques to generate a lightweight model that achieves higher performance than its dense model equivalent, especially under the presence of visual noise. Our sparse models achieve state-of-the-art results at 10% sparsity on the LRS3 dataset and outperform the dense equivalent up to 70% sparsity. We evaluate our 50% sparse model on 7 different visual noise types and achieve an overall absolute improvement of more than 2% WER compared to the dense equivalent. Our results confirm that sparse networks are more resistant to noise than dense networks.

Abstract: Comparing different age estimation methods poses a challenge due to the unreliability of published results, stemming from inconsistencies in the benchmarking process. Previous studies have reported continuous performance improvements over the past decade using specialized methods; however, our findings challenge these claims. We argue that, for age estimation tasks outside of the low-data regime, designing specialized methods is unnecessary, and the standard approach of utilizing cross-entropy loss is sufficient. This paper aims to address the benchmark shortcomings by evaluating state-of-the-art age estimation methods in a unified and comparable setting. We systematically analyze the impact of various factors, including facial alignment, facial coverage, image resolution, image representation, model architecture, and the amount of data on age estimation results. Surprisingly, these factors often exert a more significant influence than the choice of the age estimation method itself. We assess the generalization capability of each method by evaluating the cross-dataset performance for publicly available age estimation datasets. The results emphasize the importance of using consistent data preprocessing practices and establishing standardized benchmarks to ensure reliable and meaningful comparisons. The source code is available at https://github.com/paplhjak/Facial-Age-Estimation-Benchmark.

Abstract: Texture is an essential information in image representation, capturing patterns and structures. As a result, texture plays a crucial role in the manufacturing industry and is extensively studied in the fields of computer vision and pattern recognition. However, real-world textures are susceptible to defects, which can degrade image quality and cause various issues. Therefore, there is a need for accurate and effective methods to detect texture defects. In this study, a simple autoencoder and Fourier transform are employed for texture defect detection. The proposed method combines Fourier transform analysis with the reconstructed template obtained from the simple autoencoder. Fourier transform is a powerful tool for analyzing the frequency domain of images and signals. Moreover, since texture defects often exhibit characteristic changes in specific frequency ranges, analyzing the frequency domain enables effective defect detection. The proposed method demonstrates effectiveness and accuracy in detecting texture defects. Experimental results are presented to evaluate its performance and compare it with existing approaches.

Abstract: We propose a novel abstraction of the image segmentation task in the form of a combinatorial optimization problem that we call the multi-separator problem. Feasible solutions indicate for every pixel whether it belongs to a segment or a segment separator, and indicate for pairs of pixels whether or not the pixels belong to the same segment. This is in contrast to the closely related lifted multicut problem where every pixel is associated to a segment and no pixel explicitly represents a separating structure. While the multi-separator problem is NP-hard, we identify two special cases for which it can be solved efficiently. Moreover, we define two local search algorithms for the general case and demonstrate their effectiveness in segmenting simulated volume images of foam cells and filaments.

Abstract: There is a strong incentive to develop computational pathology models to i) ease the burden of tissue typology annotation from whole slide histological images; ii) transfer knowledge, e.g., tissue class separability from the withheld source domain to the distributionally shifted unlabeled target domain, and simultaneously iii) detect Open Set samples, i.e., unseen novel categories not present in the training source domain. This paper proposes a highly practical setting by addressing the abovementioned challenges in one fell swoop, i.e., source-free Open Set domain adaptation (SF-OSDA), which addresses the situation where a model pre-trained on the inaccessible source dataset can be adapted on the unlabeled target dataset containing Open Set samples. The central tenet of our proposed method is distilling knowledge from a self-supervised vision transformer trained in the target domain. We propose a novel style-based data augmentation used as hard positives for self-training a vision transformer in the target domain, yielding strongly contextualized embedding. Subsequently, semantically similar target images are clustered while the source model provides their corresponding weak pseudo-labels with unreliable confidence. Furthermore, we propose cluster relative maximum logit score (CRMLS) to rectify the confidence of the weak pseudo-labels and compute weighted class prototypes in the contextualized embedding space that are utilized for adapting the source model on the target domain. Our method significantly outperforms the previous methods, including open set detection, test-time adaptation, and SF-OSDA methods, setting the new state-of-the-art on three public histopathological datasets of colorectal cancer (CRC) assessment- Kather-16, Kather-19, and CRCTP. Our code is available at https://github.com/LTS5/Proto-SF-OSDA.

Abstract: Medical image classification is a challenging task due to the scarcity of labeled samples and class imbalance caused by the high variance in disease prevalence. Semi-supervised learning (SSL) methods can mitigate these challenges by leveraging both labeled and unlabeled data. However, SSL methods for medical image classification need to address two key challenges: (1) estimating reliable pseudo-labels for the images in the unlabeled dataset and (2) reducing biases caused by class imbalance. In this paper, we propose a novel SSL approach, SPLAL, that effectively addresses these challenges. SPLAL leverages class prototypes and a weighted combination of classifiers to predict reliable pseudo-labels over a subset of unlabeled images. Additionally, we introduce alignment loss to mitigate model biases toward majority classes. To evaluate the performance of our proposed approach, we conduct experiments on two publicly available medical image classification benchmark datasets: the skin lesion classification (ISIC 2018) and the blood cell classification dataset (BCCD). The experimental results empirically demonstrate that our approach outperforms several state-of-the-art SSL methods over various evaluation metrics. Specifically, our proposed approach achieves a significant improvement over the state-of-the-art approach on the ISIC 2018 dataset in both Accuracy and F1 score, with relative margins of 2.24\% and 11.40\%, respectively. Finally, we conduct extensive ablation experiments to examine the contribution of different components of our approach, validating its effectiveness.

Abstract: Age and gender recognition in the wild is a highly challenging task: apart from the variability of conditions, pose complexities, and varying image quality, there are cases where the face is partially or completely occluded. We present MiVOLO (Multi Input VOLO), a straightforward approach for age and gender estimation using the latest vision transformer. Our method integrates both tasks into a unified dual input/output model, leveraging not only facial information but also person image data. This improves the generalization ability of our model and enables it to deliver satisfactory results even when the face is not visible in the image. To evaluate our proposed model, we conduct experiments on four popular benchmarks and achieve state-of-the-art performance, while demonstrating real-time processing capabilities. Additionally, we introduce a novel benchmark based on images from the Open Images Dataset. The ground truth annotations for this benchmark have been meticulously generated by human annotators, resulting in high accuracy answers due to the smart aggregation of votes. Furthermore, we compare our model's age recognition performance with human-level accuracy and demonstrate that it significantly outperforms humans across a majority of age ranges. Finally, we grant public access to our models, along with the code for validation and inference. In addition, we provide extra annotations for used datasets and introduce our new benchmark.

Abstract: Large medical imaging datasets can be cheaply and quickly annotated with low-confidence, weak labels (e.g., radiological scores). Access to high-confidence labels, such as histology-based diagnoses, is rare and costly. Pretraining strategies, like contrastive learning (CL) methods, can leverage unlabeled or weakly-annotated datasets. These methods typically require large batch sizes, which poses a difficulty in the case of large 3D images at full resolution, due to limited GPU memory. Nevertheless, volumetric positional information about the spatial context of each 2D slice can be very important for some medical applications. In this work, we propose an efficient weakly-supervised positional (WSP) contrastive learning strategy where we integrate both the spatial context of each 2D slice and a weak label via a generic kernel-based loss function. We illustrate our method on cirrhosis prediction using a large volume of weakly-labeled images, namely radiological low-confidence annotations, and small strongly-labeled (i.e., high-confidence) datasets. The proposed model improves the classification AUC by 5% with respect to a baseline model on our internal dataset, and by 26% on the public LIHC dataset from the Cancer Genome Atlas. The code is available at: https://github.com/Guerbet-AI/wsp-contrastive.

Abstract: Salient objects attract human attention and usually stand out clearly from their surroundings. In contrast, camouflaged objects share similar colors or textures with the environment. In this case, salient objects are typically non-camouflaged, and camouflaged objects are usually not salient. Due to this inherent contradictory attribute, we introduce an uncertainty-aware learning pipeline to extensively explore the contradictory information of salient object detection (SOD) and camouflaged object detection (COD) via data-level and task-wise contradiction modeling. We first exploit the dataset correlation of these two tasks and claim that the easy samples in the COD dataset can serve as hard samples for SOD to improve the robustness of the SOD model. Based on the assumption that these two models should lead to activation maps highlighting different regions of the same input image, we further introduce a contrastive module with a joint-task contrastive learning framework to explicitly model the contradictory attributes of these two tasks. Different from conventional intra-task contrastive learning for unsupervised representation learning, our contrastive module is designed to model the task-wise correlation, leading to cross-task representation learning. To better understand the two tasks from the perspective of uncertainty, we extensively investigate the uncertainty estimation techniques for modeling the main uncertainties of the two tasks, namely task uncertainty (for SOD) and data uncertainty (for COD), and aiming to effectively estimate the challenging regions for each task to achieve difficulty-aware learning. Experimental results on benchmark datasets demonstrate that our solution leads to both state-of-the-art performance and informative uncertainty estimation.

Abstract: To serve the intricate and varied demands of image editing, precise and flexible manipulation of image content is indispensable. Recently, DragGAN has achieved impressive editing results through point-based manipulation. However, we have observed that DragGAN struggles with miss tracking, where DragGAN encounters difficulty in effectively tracking the desired handle points, and ambiguous tracking, where the tracked points are situated within other regions that bear resemblance to the handle points. To deal with the above issues, we propose FreeDrag, which adopts a feature-oriented approach to free the burden on point tracking within the point-oriented methodology of DragGAN. The FreeDrag incorporates adaptive template features, line search, and fuzzy localization techniques to perform stable and efficient point-based image editing. Extensive experiments demonstrate that our method is superior to the DragGAN and enables stable point-based editing in challenging scenarios with similar structures, fine details, or under multi-point targets.

Abstract: In this paper, we present a deforestation estimation method based on attention guided UNet architecture using Electro-Optical (EO) and Synthetic Aperture Radar (SAR) satellite imagery. For optical images, Landsat-8 and for SAR imagery, Sentinel-1 data have been used to train and validate the proposed model. Due to the unavailability of temporally and spatially collocated data, individual model has been trained for each sensor. During training time Landsat-8 model achieved training and validation pixel accuracy of 93.45% and Sentinel-2 model achieved 83.87% pixel accuracy. During the test set evaluation, the model achieved pixel accuracy of 84.70% with F1-Score of 0.79 and IoU of 0.69.

Abstract: With the advance of text-to-image models (e.g., Stable Diffusion) and corresponding personalization techniques such as DreamBooth and LoRA, everyone can manifest their imagination into high-quality images at an affordable cost. Subsequently, there is a great demand for image animation techniques to further combine generated static images with motion dynamics. In this report, we propose a practical framework to animate most of the existing personalized text-to-image models once and for all, saving efforts in model-specific tuning. At the core of the proposed framework is to insert a newly initialized motion modeling module into the frozen text-to-image model and train it on video clips to distill reasonable motion priors. Once trained, by simply injecting this motion modeling module, all personalized versions derived from the same base T2I readily become text-driven models that produce diverse and personalized animated images. We conduct our evaluation on several public representative personalized text-to-image models across anime pictures and realistic photographs, and demonstrate that our proposed framework helps these models generate temporally smooth animation clips while preserving the domain and diversity of their outputs. Code and pre-trained weights will be publicly available at https://animatediff.github.io/ .

Abstract: The field of text-conditioned image generation has made unparalleled progress with the recent advent of latent diffusion models. While remarkable, as the complexity of given text input increases, the state-of-the-art diffusion models may still fail in generating images which accurately convey the semantics of the given prompt. Furthermore, it has been observed that such misalignments are often left undetected by pretrained multi-modal models such as CLIP. To address these problems, in this paper we explore a simple yet effective decompositional approach towards both evaluation and improvement of text-to-image alignment. In particular, we first introduce a Decompositional-Alignment-Score which given a complex prompt decomposes it into a set of disjoint assertions. The alignment of each assertion with generated images is then measured using a VQA model. Finally, alignment scores for different assertions are combined aposteriori to give the final text-to-image alignment score. Experimental analysis reveals that the proposed alignment metric shows significantly higher correlation with human ratings as opposed to traditional CLIP, BLIP scores. Furthermore, we also find that the assertion level alignment scores provide a useful feedback which can then be used in a simple iterative procedure to gradually increase the expression of different assertions in the final image outputs. Human user studies indicate that the proposed approach surpasses previous state-of-the-art by 8.7% in overall text-to-image alignment accuracy. Project page for our paper is available at https://1jsingh.github.io/divide-evaluate-and-refine

Abstract: We propose a self-supervised method for learning representations based on spatial audio-visual correspondences in egocentric videos. In particular, our method leverages a masked auto-encoding framework to synthesize masked binaural audio through the synergy of audio and vision, thereby learning useful spatial relationships between the two modalities. We use our pretrained features to tackle two downstream video tasks requiring spatial understanding in social scenarios: active speaker detection and spatial audio denoising. We show through extensive experiments that our features are generic enough to improve over multiple state-of-the-art baselines on two public challenging egocentric video datasets, EgoCom and EasyCom. Project: http://vision.cs.utexas.edu/projects/ego_av_corr.

Abstract: In this paper, we introduce Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity. Our model offers two key advantages: semantic-awareness and granularity-abundance. To achieve semantic-awareness, we consolidate multiple datasets across three granularities and introduce decoupled classification for objects and parts. This allows our model to capture rich semantic information. For the multi-granularity capability, we propose a multi-choice learning scheme during training, enabling each click to generate masks at multiple levels that correspond to multiple ground-truth masks. Notably, this work represents the first attempt to jointly train a model on SA-1B, generic, and part segmentation datasets. Experimental results and visualizations demonstrate that our model successfully achieves semantic-awareness and granularity-abundance. Furthermore, combining SA-1B training with other segmentation tasks, such as panoptic and part segmentation, leads to performance improvements. We will provide code and a demo for further exploration and evaluation.