Related papers: SAC-ViT: Semantic-Aware Clustering Vision Transfor…

This paper proposes a novel communication-efficient Split Learning (SL) framework, named Attention-based Double Compression (ADC), which reduces the communication overhead required for transmitting intermediate Vision Transformers…

Transformers have been widely used in numerous vision problems especially for visual recognition and detection. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the…

Test-Time Training (TTT) has recently emerged as a promising direction for efficient sequence modeling. TTT reformulates attention operation as an online learning problem, constructing a compact inner model from key-value pairs at test…

Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts…

This work presents a simple vision transformer design as a strong baseline for object localization and instance segmentation tasks. Transformers recently demonstrate competitive performance in image classification tasks. To adopt ViT to…

The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challenged. However, models such as the Vision Transformer (ViT)…

High runtime memory and high latency puts significant constraint on Vision Transformer training and inference, especially on edge devices. Token pruning reduces the number of input tokens to the ViT based on importance criteria of each…

Vision transformers (ViTs) are quickly becoming the de-facto architecture for computer vision, yet we understand very little about why they work and what they learn. While existing studies visually analyze the mechanisms of convolutional…

Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. This representation trades spatial granularity for embedding…

Mobile Edge Caching (MEC) is a revolutionary technology for the Sixth Generation (6G) of wireless networks with the promise to significantly reduce users' latency via offering storage capacities at the edge of the network. The efficiency of…

Transformer models have made tremendous progress in various fields in recent years. In the field of computer vision, vision transformers (ViTs) also become strong alternatives to convolutional neural networks (ConvNets), yet they have not…

Vision Transformers (ViTs) have demonstrated remarkable capabilities in learning representations, but their performance is compromised when applied to unseen domains. Previous methods either engage in prompt learning during the training…

Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. However, modeling global correlations with multi-head self-attention (MSA) layers leads to two widely recognized issues: the massive…

Vision Transformers (ViTs), extensively pre-trained on large-scale datasets, have become essential to foundation models, allowing excellent performance on diverse downstream tasks with minimal adaptation. Consequently, there is growing…

We study a crucial yet often overlooked issue inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which hurt the performance of ViTs in downstream dense prediction tasks such as semantic…

Vision Transformer (ViT) based autoencoders often underutilize the global Class token and employ static attention mechanisms, limiting both generative control and optimization efficiency. This paper introduces ViTCAE, a framework that…

Recently, Vision Transformers (ViTs) have attracted a lot of attention in the field of computer vision. Generally, the powerful representative capacity of ViTs mainly benefits from the self-attention mechanism, which has a high computation…

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…

Vision Transformers (ViTs) are widely adopted in medical imaging tasks, and some existing efforts have been directed towards vision-language training for Chest X-rays (CXRs). However, we envision that there still exists a potential for…

Vision Transformers (ViTs) have demonstrated outstanding performance in computer vision tasks, yet their high computational complexity prevents their deployment in computing resource-constrained environments. Various token pruning…