Related papers: LocalViT: Analyzing Locality in Vision Transformer…
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-attention networks have proven to be of profound value for its strength of capturing global dependencies. In this work, we propose to model localness for self-attention networks, which enhances the ability of capturing useful local…
Vision Transformers (ViTs) have become prominent models for solving various vision tasks. However, the interpretability of ViTs has not kept pace with their promising performance. While there has been a surge of interest in developing {\it…
Vision Transformers (ViTs) have demonstrated remarkable potential in image processing tasks by utilizing self-attention mechanisms to capture global relationships within data. However, their scalability is hindered by significant…
With the advent of state of the art nature-inspired pure attention based models i.e. transformers, and their success in natural language processing (NLP), their extension to machine vision (MV) tasks was inevitable and much felt.…
In the last decade, convolutional neural networks (ConvNets) have dominated and achieved state-of-the-art performances in a variety of medical imaging applications. However, the performances of ConvNets are still limited by lacking the…
Discovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud. Most existing methods focus on designing efficient local feature extractors while…
Driving in a complex urban environment is a difficult task that requires a complex decision policy. In order to make informed decisions, one needs to gain an understanding of the long-range context and the importance of other vehicles. In…
Vision Transformer (ViT) has shown great potential for various visual tasks due to its ability to model long-range dependency. However, ViT requires a large amount of computing resource to compute the global self-attention. In this work, we…
We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble tokens from various stages of the vision transformer into…
Deep neural networks have reached human-level performance on many computer vision tasks. However, the objectives used to train these networks enforce only that similar images are embedded at similar locations in the representation space,…
Self-attention mechanism has been a key factor in the recent progress of Vision Transformer (ViT), which enables adaptive feature extraction from global contexts. However, existing self-attention methods either adopt sparse global attention…
Understanding the mechanisms underlying deep neural networks remains a fundamental challenge in machine learning and computer vision. One promising, yet only preliminarily explored approach, is feature inversion, which attempts to…
Model editing aims to data-efficiently correct predictive errors of large pre-trained models while ensuring generalization to neighboring failures and locality to minimize unintended effects on unrelated examples. While significant progress…
Deep convolutional neural networks are used to address many computer vision problems, including video prediction. The task of video prediction requires analyzing the video frames, temporally and spatially, and constructing a model of how…
We attempt to reduce the computational costs in vision transformers (ViTs), which increase quadratically in the token number. We present a novel training paradigm that trains only one ViT model at a time, but is capable of providing…
Attention-based models such as transformers have shown outstanding performance on dense prediction tasks, such as semantic segmentation, owing to their capability of capturing long-range dependency in an image. However, the benefit of…
Vision transformers (ViTs) are usually considered to be less light-weight than convolutional neural networks (CNNs) due to the lack of inductive bias. Recent works thus resort to convolutions as a plug-and-play module and embed them in…
Vision transformers (ViTs) have demonstrated remarkable performance across various visual tasks. However, ViT models suffer from substantial computational and memory requirements, making it challenging to deploy them on resource-constrained…
Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…