相关论文: What Do Self-Supervised Vision Transformers Learn?

Self-supervision has shown outstanding results for natural language processing, and more recently, for image recognition. Simultaneously, vision transformers and its variants have emerged as a promising and scalable alternative to…

Contrastive learning (CL)-based self-supervised learning models learn visual representations in a pairwise manner. Although the prevailing CL model has achieved great progress, in this paper, we uncover an ever-overlooked phenomenon: When…

Self-supervised learning (SSL) is an approach to extract useful feature representations from unlabeled data, and enable fine-tuning on downstream tasks with limited labeled examples. Self-pretraining is a SSL approach that uses the curated…

Recent advances in language modeling have witnessed the rise of highly desirable emergent capabilities, such as reasoning and in-context learning. However, vision models have yet to exhibit comparable progress in these areas. In this paper,…

The vision-language navigation (VLN) task requires an agent to reach a target with the guidance of natural language instruction. Previous works learn to navigate step-by-step following an instruction. However, these works may fail to…

The success of Vision Transformer (ViT) has been widely reported on a wide range of image recognition tasks. ViT can learn global dependencies superior to CNN, yet CNN's inherent locality can substitute for expensive training resources.…

The existing contrastive learning methods widely adopt one-hot instance discrimination as pretext task for self-supervised learning, which inevitably neglects rich inter-instance similarities among natural images, then leading to potential…

Recent progress in contrastive learning has revolutionized unsupervised representation learning. Concretely, multiple views (augmentations) from the same image are encouraged to map to the similar embeddings, while views from different…

Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an…

Standard contrastive learning approaches usually require a large number of negatives for effective unsupervised learning and often exhibit slow convergence. We suspect this behavior is due to the suboptimal selection of negatives used for…

Learning representations that transfer well to diverse downstream tasks remains a central challenge in representation learning. Existing paradigms -- contrastive learning, self-supervised masking, and denoising auto-encoders -- balance this…

In information retrieval, training reranking models mainly focuses on two types of objectives: metric learning (e.g. contrastive loss to increase the predicted scores on relevant query-document pairs) and classification (binary label…

Recent breakthroughs in the field of semi-supervised learning have achieved results that match state-of-the-art traditional supervised learning methods. Most successful semi-supervised learning approaches in computer vision focus on…

Transformers, composed of multiple self-attention layers, hold strong promises toward a generic learning primitive applicable to different data modalities, including the recent breakthroughs in computer vision achieving state-of-the-art…

Self-supervised learning methods are gaining increasing traction in computer vision due to their recent success in reducing the gap with supervised learning. In natural language processing (NLP) self-supervised learning and transformers are…

To make sense of their surroundings, intelligent systems must transform complex sensory inputs to structured codes that are reduced to task-relevant information such as object category. Biological agents achieve this in a largely autonomous…

While contrastive learning (CL) shows considerable promise in self-supervised representation learning, its deployment on resource-constrained devices remains largely underexplored. The substantial computational demands required for training…

Vision Transformers (ViTs) have revolutionized computer vision tasks with their exceptional performance. However, the introduction of privacy regulations such as GDPR and CCPA has brought new challenges to them. These laws grant users the…

This paper proposes a working recipe of using Vision Transformer (ViT) in class incremental learning. Although this recipe only combines existing techniques, developing the combination is not trivial. Firstly, naive application of ViT to…

Convolutional networks and vision transformers have different forms of pairwise interactions, pooling across layers and pooling at the end of the network. Does the latter really need to be different? As a by-product of pooling, vision…