相关论文: Global Vision Transformer Pruning with Hessian-Awa…

The quadratic computational complexity to the number of tokens limits the practical applications of Vision Transformers (ViTs). Several works propose to prune redundant tokens to achieve efficient ViTs. However, these methods generally…

Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We…

Although using convolutional neural networks (CNNs) as backbones achieves great successes in computer vision, this work investigates a simple backbone network useful for many dense prediction tasks without convolutions. Unlike the…

Vision Transformers (ViTs) have outperformed traditional Convolutional Neural Network architectures and achieved state-of-the-art results in various computer vision tasks. Since ViTs are computationally expensive, the models either have to…

Attention-based neural networks such as the Vision Transformer (ViT) have recently attained state-of-the-art results on many computer vision benchmarks. Scale is a primary ingredient in attaining excellent results, therefore, understanding…

Transformers have emerged as a competitive alternative to convnets in vision tasks, yet they lack the architectural inductive bias of convnets, which may hinder their potential performance. Specifically, Vision Transformers (ViTs) are not…

Recently, vision transformers (ViTs) have superseded convolutional neural networks in numerous applications, including classification, detection, and segmentation.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…

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…

Vision Transformers (ViTs) leverage the transformer architecture to effectively capture global context, demonstrating strong performance in computer vision tasks. A major challenge in ViT hardware acceleration is that the model family…

Vision Transformers (ViTs) represent a groundbreaking shift in machine learning approaches to computer vision. Unlike traditional approaches, ViTs employ the self-attention mechanism, which has been widely used in natural language…

Transformer-based architectures have revolutionized the landscape of deep learning. In computer vision domain, Vision Transformer demonstrates remarkable performance on par with or even surpassing that of convolutional neural networks.…

This study evaluates the trade-offs between convolutional and transformer-based architectures on both medical and general-purpose image classification benchmarks. We use ResNet-18 as our baseline and introduce a fine-tuning strategy applied…

Vision Transformers (ViTs) have achieved remarkable success across various vision tasks, yet their deployment is often hindered by prohibitive computational costs. While structured weight pruning and token compression have emerged as…

Transformer architecture has gained popularity due to its ability to scale with large dataset. Consequently, there is a need to reduce the model size and latency, especially for on-device deployment. We focus on vision transformer proposed…

Pruning is an effective method to reduce the memory footprint and FLOPs associated with neural network models. However, existing structured-pruning methods often result in significant accuracy degradation for moderate pruning levels. To…

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…

Pretrained vision foundation models deliver strong performance across tasks with limited fine-tuning. However, their Vision Transformer (ViT) backbones impose high inference costs, limiting deployment on resource-constrained devices. In…

Several video understanding tasks, such as natural language temporal video grounding, temporal activity localization, and audio description generation, require "temporally dense" reasoning over frames sampled at high temporal resolution.…

Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure into regional and local feature extraction procedures that each…

Vision transformers (ViTs) inherited the success of NLP but their structures have not been sufficiently investigated and optimized for visual tasks. One of the simplest solutions is to directly search the optimal one via the widely used…