相关论文: $E(2)$-Equivariant Vision Transformer

This work investigates a simple yet powerful dense prediction task adapter for Vision Transformer (ViT). Unlike recently advanced variants that incorporate vision-specific inductive biases into their architectures, the plain ViT suffers…

Vision-Language (VL) models have gained significant research focus, enabling remarkable advances in multimodal reasoning. These architectures typically comprise a vision encoder, a Large Language Model (LLM), and a projection module that…

Vision transformers (ViTs) encoding an image as a sequence of patches bring new paradigms for semantic segmentation.We present an efficient framework of representation separation in local-patch level and global-region level for semantic…

Currently, vision encoder models like Vision Transformers (ViTs) typically excel at image recognition tasks but cannot simultaneously support text recognition like human visual recognition. To address this limitation, we propose UNIT, a…

In this paper, we present a comparative analysis of various self-supervised Vision Transformers (ViTs), focusing on their local representative power. Inspired by large language models, we examine the abilities of ViTs to perform various…

Generalizing a pretrained model to unseen datasets without retraining is an essential step toward a foundation model. However, achieving such cross-dataset, fully inductive inference is difficult in graph-structured data where feature…

Non-overlapping patch-wise convolution is the default image tokenizer for all state-of-the-art vision Transformer (ViT) models. Even though many ViT variants have been proposed to improve its efficiency and accuracy, little research on…

Vision Transformers (ViTs) outperforms convolutional neural networks (CNNs) in several vision tasks with its global modeling capabilities. However, ViT lacks the inductive bias inherent to convolution making it require a large amount of…

Convolutional Neural Networks (CNNs) for computer vision sometimes struggle with understanding images in a global context, as they mainly focus on local patterns. On the other hand, Vision Transformers (ViTs), inspired by models originally…

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…

Vision Transformers (ViTs) have demonstrated strong capabilities in capturing global dependencies but often struggle to efficiently represent fine-grained local details. Existing multi-scale approaches alleviate this issue by integrating…

Transformers, a groundbreaking architecture proposed for Natural Language Processing (NLP), have also achieved remarkable success in Computer Vision. A cornerstone of their success lies in the attention mechanism, which models relationships…

Vision Transformer (ViT) is a pioneering deep learning framework that can address real-world computer vision issues, such as image classification and object recognition. Importantly, ViTs are proven to outperform traditional deep learning…

Unsupervised domain adaptation (UDA) aims to transfer the knowledge learnt from a labeled source domain to an unlabeled target domain. Previous work is mainly built upon convolutional neural networks (CNNs) to learn domain-invariant…

Vision transformers have achieved encouraging progress in various computer vision tasks. A common belief is that this is attributed to the capability of self-attention in modeling the global dependencies among feature tokens. However,…

In robot learning, Vision Transformers (ViTs) are standard for visual perception, yet most methods discard valuable information by using only the final layer's features. We argue this provides an insufficient representation and propose the…

We combine vision transformers with operator learning to solve diverse inverse problems described by partial differential equations (PDEs). Our approach, named ViTO, combines a U-Net based architecture with a vision transformer. We apply…

In the field of EEG-based gaze prediction, the application of deep learning to interpret complex neural data poses significant challenges. This study evaluates the effectiveness of pre-processing techniques and the effect of additional…

We introduce GVIT, a classification framework that abandons conventional pixel or patch grid input representations in favor of a compact set of learnable 2D Gaussians. Each image is encoded as a few hundred Gaussians whose positions,…

Deep learning models are increasingly utilized on resource-constrained edge devices for real-time data analytics. Recently, Vision Transformer and their variants have shown exceptional performance in various computer vision tasks. However,…