Related papers: Learning Cross-modal Contrastive Features for Vide…

Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Since the model is sensitive to domain shift, unsupervised…

Visual data driven dictionaries have been successfully employed for various object recognition and classification tasks. However, the task becomes more challenging if the training and test data are from contrasting domains. In this paper,…

Deep domain adaption has emerged as a new learning technique to address the lack of massive amounts of labeled data. Compared to conventional methods, which learn shared feature subspaces or reuse important source instances with shallow…

We introduce a novel unsupervised domain adaptation approach for object detection. We aim to alleviate the imperfect translation problem of pixel-level adaptations, and the source-biased discriminativity problem of feature-level adaptations…

Recent advances in domain adaptation reveal that adversarial learning on deep neural networks can learn domain invariant features to reduce the shift between source and target domains. While such adversarial approaches achieve domain-level…

We introduce a novel approach to unsupervised and semi-supervised domain adaptation for semantic segmentation. Unlike many earlier methods that rely on adversarial learning for feature alignment, we leverage contrastive learning to bridge…

Deep learning models for dermatological image analysis remain sensitive to acquisition variability and domain-specific visual characteristics, leading to performance degradation when deployed in clinical settings. We investigate how visual…

Recent works have advanced the performance of self-supervised representation learning by a large margin. The core among these methods is intra-image invariance learning. Two different transformations of one image instance are considered as…

Contrastive learning has delivered impressive results for various tasks in the self-supervised regime. However, existing approaches optimize for learning representations specific to downstream scenarios, i.e., \textit{global}…

Object recognition from images means to automatically find object(s) of interest and to return their category and location information. Benefiting from research on deep learning, like convolutional neural networks~(CNNs) and generative…

We propose a supervised contrastive learning framework for video representation learning that leverages temporally global context. We introduce a video to image aggregation strategy that spatially arranges multiple frames from each video…

Due to the numerous potential applications in visual surveillance and nighttime driving, recognizing human action in low-light conditions remains a difficult problem in computer vision. Existing methods separate action recognition and dark…

Despite the successes of deep neural networks on many challenging vision tasks, they often fail to generalize to new test domains that are not distributed identically to the training data. The domain adaptation becomes more challenging for…

Long-form video understanding requires designing approaches that are able to temporally localize activities or language. End-to-end training for such tasks is limited by the compute device memory constraints and lack of temporal annotations…

We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy…

Domain adaptation aims at adapting the knowledge acquired on a source domain to a new different but related target domain. Several approaches have beenproposed for classification tasks in the unsupervised scenario, where no labeled target…

Generic object detection has been immensely promoted by the development of deep convolutional neural networks in the past decade. However, in the domain shift circumstance, the changes in weather, illumination, etc., often cause domain gap,…

Few-shot video action recognition is an effective approach to recognizing new categories with only a few labeled examples, thereby reducing the challenges associated with collecting and annotating large-scale video datasets. Existing…

Existing unsupervised domain adaptation methods based on adversarial learning have achieved good performance in several medical imaging tasks. However, these methods focus only on global distribution adaptation and ignore distribution…

Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In…