Related papers: ViT-Calibrator: Decision Stream Calibration for Vi…

We introduce Contextual Vision Transformers (ContextViT), a method designed to generate robust image representations for datasets experiencing shifts in latent factors across various groups. Derived from the concept of in-context learning,…

This paper investigates how to efficiently deploy vision transformers on edge devices for small workloads. Recent methods reduce the latency of transformer neural networks by removing or merging tokens, with small accuracy degradation.…

Vision transformers (ViTs) have been successfully deployed in a variety of computer vision tasks, but they are still vulnerable to adversarial samples. Transfer-based attacks use a local model to generate adversarial samples and directly…

Vision Transformers (ViTs) mark a revolutionary advance in neural networks with their token mixer's powerful global context capability. However, the pairwise token affinity and complex matrix operations limit its deployment on…

The Vision Transformer (ViT) architecture has emerged as the backbone of choice for state-of-the-art deep models for computer vision applications. However, ViTs are ill-suited for private inference using secure multi-party computation (MPC)…

As Vision Transformers (ViTs) are increasingly adopted in sensitive vision applications, there is a growing demand for improved interpretability. This has led to efforts to forward-align these models with carefully annotated abstract,…

Recent advances in Vision Transformers (ViTs) have significantly advanced semantic segmentation performance. However, their adaptation to new target domains remains challenged by distribution shifts, which often disrupt global attention…

Vision Transformers (ViTs) have successfully been applied to image classification problems where large annotated datasets are available. On the other hand, when fewer annotations are available, such as in biomedical applications, image…

Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions. Despite having…

The recently proposed Visual image Transformers (ViT) with pure attention have achieved promising performance on image recognition tasks, such as image classification. However, the routine of the current ViT model is to maintain a…

Vision Transformer (ViT) demonstrates that Transformer for natural language processing can be applied to computer vision tasks and result in comparable performance to convolutional neural networks (CNN), which have been studied and adopted…

Transformers are state-of-the-art deep learning models that are composed of stacked attention and point-wise, fully connected layers designed for handling sequential data. Transformers are not only ubiquitous throughout Natural Language…

Vision Transformer (ViT) models have made breakthroughs in image embedding extraction, which provide state-of-the-art performance in tasks such as zero-shot image classification. However, the models suffer from a high computational burden.…

Self-attention in Transformers comes with a high computational cost because of their quadratic computational complexity, but their effectiveness in addressing problems in language and vision has sparked extensive research aimed at enhancing…

Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the…

Vision transformer (ViT) and its variants have swept through visual learning leaderboards and offer state-of-the-art accuracy in tasks such as image classification, object detection, and semantic segmentation by attending to different parts…

This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention operations in every layer, we identify that these operations are highly correlated across layers -- a key…

Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self-attention or early-stage convolutions are thus utilized,…

Vision Transformers (ViTs) have emerged as popular models in computer vision, demonstrating state-of-the-art performance across various tasks. This success typically follows a two-stage strategy involving pre-training on large-scale…

This paper presents the Large Vision Diffusion Transformer (LaVin-DiT), a scalable and unified foundation model designed to tackle over 20 computer vision tasks in a generative framework. Unlike existing large vision models directly adapted…