Related papers: Spectral Vision Transformer for Efficient Tokeniza…

Vision Transformers (ViT) have emerged as the de-facto choice for numerous industry grade vision solutions. But their inference cost can be prohibitive for many settings, as they compute self-attention in each layer which suffers from…

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…

In the wake of Masked Image Modeling (MIM), a diverse range of plain, non-hierarchical Vision Transformer (ViT) models have been pre-trained with extensive datasets, offering new paradigms and significant potential for semantic…

The vision transformer splits each image into a sequence of tokens with fixed length and processes the tokens in the same way as words in natural language processing. More tokens normally lead to better performance but considerably…

Vision Transformer (ViT) has emerged as a powerful architecture in the realm of modern computer vision. However, its application in certain imaging fields, such as microscopy and satellite imaging, presents unique challenges. In these…

The architecture of transformers, which recently witness booming applications in vision tasks, has pivoted against the widespread convolutional paradigm. Relying on the tokenization process that splits inputs into multiple tokens,…

In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViTs that computes the classification loss on an additional…

Parameter inference is a crucial task in modern cosmology that requires accurate and fast computational methods to handle the high precision and volume of observational datasets. In this study, we explore a hybrid vision transformer, the…

The cost of deploying vision transformers increasingly represents a barrier to wider industrial adoption. Existing compression techniques require additional end-to-end fine-tuning or incur a significant drawback to energy efficiency, making…

Vision Transformers rely on fixed patch tokens that ignore the spatial and semantic structure of images. In this work, we introduce an end-to-end differentiable tokenizer that adapts to image content with pixel-level granularity while…

Vision Transformers (ViTs) have emerged as the backbone of many segmentation models, consistently achieving state-of-the-art (SOTA) performance. However, their success comes at a significant computational cost. Image token pruning is one of…

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…

We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory requirement from the depth of the model, Reversible Vision Transformers enable scaling up architectures…

Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks recently. However, their heavy computation costs remain daunting for resource-limited devices. To address this, researchers have dedicated…

Hyperspectral imaging provides detailed spectral information and holds significant potential for monitoring of greenhouse gases (GHGs). However, its application is constrained by limited spatial coverage and infrequent revisit times. In…

Recently, vision transformers (ViTs) have superseded convolutional neural networks in numerous applications, including classification, detection, and segmentation. However, the high computational requirements of ViTs hinder their widespread…

While CNNs were long considered state of the art for image processing, the introduction of Transformer architectures has challenged this position. While achieving excellent results in image classification and segmentation, Transformers…

Can a lightweight Vision Transformer (ViT) match or exceed the performance of Convolutional Neural Networks (CNNs) like ResNet on small datasets with small image resolutions? This report demonstrates that a pure ViT can indeed achieve…

Time series forecasting plays a crucial role in decision-making across various domains, but it presents significant challenges. Recent studies have explored image-driven approaches using computer vision models to address these challenges,…

The formidable accomplishment of Transformers in natural language processing has motivated the researchers in the computer vision community to build Vision Transformers. Compared with the Convolution Neural Networks (CNN), a Vision…