Related papers: Vis-TOP: Visual Transformer Overlay Processor
This paper tackles a significant challenge faced by Vision Transformers (ViTs): their constrained scalability across different image resolutions. Typically, ViTs experience a performance decline when processing resolutions different from…
Vision transformers (ViTs) have demonstrated their superior accuracy for computer vision tasks compared to convolutional neural networks (CNNs). However, ViT models are often computation-intensive for efficient deployment on…
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,…
Learning efficient and expressive visual representation has long been the pursuit of computer vision research. While Vision Transformers (ViTs) gradually replace traditional Convolutional Neural Networks (CNNs) as more scalable vision…
Following the success of the natural language processing, the transformer for vision applications has attracted significant attention in recent years due to its excellent performance. However, existing deep learning hardware accelerators…
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…
The remarkable performance of the Transformer architecture in natural language processing has recently also triggered broad interest in Computer Vision. Among other merits, Transformers are witnessed as capable of learning long-range…
We study the training of Vision Transformers for semi-supervised image classification. Transformers have recently demonstrated impressive performance on a multitude of supervised learning tasks. Surprisingly, we show Vision Transformers…
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…
The feature maps of vision encoders are fundamental to myriad modern AI tasks, ranging from core perception algorithms (e.g. semantic segmentation, object detection, depth perception, etc.) to modern multimodal understanding in…
Specialized accelerators for tensor-operations, such as blocked-matrix operations and multi-dimensional convolutions, have been emerged as powerful architecture choices for high-performance Deep-Learning computing. The rapid development of…
Despite the exciting performance, Transformer is criticized for its excessive parameters and computation cost. However, compressing Transformer remains as an open problem due to its internal complexity of the layer designs, i.e., Multi-Head…
Transformer is a new kind of neural architecture which encodes the input data as powerful features via the attention mechanism. Basically, the visual transformers first divide the input images into several local patches and then calculate…
Transformers and their derivatives have achieved state-of-the-art performance across text, vision, and speech recognition tasks. However, minimal effort has been made to train transformers capable of evaluating the output quality of other…
Vision Transformer has demonstrated impressive success across various vision tasks. However, its heavy computation cost, which grows quadratically with respect to the token sequence length, largely limits its power in handling large feature…
Vision-based Transformer have shown huge application in the perception module of autonomous driving in terms of predicting accurate 3D bounding boxes, owing to their strong capability in modeling long-range dependencies between the visual…
This paper presents a novel approach to address the challenges of understanding the prediction process and debugging prediction errors in Vision Transformers (ViT), which have demonstrated superior performance in various computer vision…
The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers…
Transformers have demonstrated great power in the recent development of large foundational models. In particular, the Vision Transformer (ViT) has brought revolutionary changes to the field of vision, achieving significant accomplishments…
We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. Our method leverages global context self-attention modules, joint with standard local…