paper-with-me

Papers

Can Vision Transformers Perform Convolution?

2021-11-02 · Shanda Li, Xiangning Chen, Di He, Cho-Jui Hsieh

Several recent studies have demonstrated that attention-based networks, such as Vision Transformer (ViT), can outperform Convolutional Neural Networks (CNNs) on several computer vision tasks without using convolutional layers. This naturally leads to the following questions: Can a self-attention layer of ViT express any convolution operation? In this work, we prove that a single ViT layer with image patches as the input can perform any convolution operation constructively, where the multi-head attention mechanism and the relative positional encoding play essential roles. We further provide a lower bound on the number of heads for Vision Transformers to express CNNs. Corresponding with our analysis, experimental results show that the construction in our proof can help inject convolutional bias into Transformers and significantly improve the performance of ViT in low data regimes.

📄 PDF Abstract BibTeX arXiv:2111.01353

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음

Similar Papers 제목 키워드 기반

On Convolutional Vision Transformers for Yield Prediction

2024-02-08 · Alvin Inderka, Florian Huber, Volker Steinhage

While a variety of methods offer good yield prediction on histogrammed remote sensing data, vision Transformers are only sparsely represented in the literature. The Convolution vision Transformer (CvT) is being tested to…

Prediction

CvT: Introducing Convolutions to Vision Transformers

2021-03-29 · ICCV 2021 10 · Haiping Wu, Bin Xiao, Noel Codella, Mengchen Liu 외

We present in this paper a new architecture, named Convolutional vision Transformer (CvT), that improves Vision Transformer (ViT) in performance and efficiency by introducing convolutions into ViT to yield the best of bo…

Image Classification

A survey of the Vision Transformers and their CNN-Transformer based Variants

2023-05-17 · Asifullah Khan, Zunaira Rauf, Anabia Sohail, Abdul Rehman 외

Vision transformers have become popular as a possible substitute to convolutional neural networks (CNNs) for a variety of computer vision applications. These transformers, with their ability to focus on global relationsh…

Survey

Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition

2021-06-09 · Ziyuan Huang, Zhiwu Qing, Xiang Wang, Yutong Feng 외

With the recent surge in the research of vision transformers, they have demonstrated remarkable potential for various challenging computer vision applications, such as image recognition, point cloud classification as wel…

Action RecognitionPoint Cloud ClassificationPredictionVideo Understanding

Interpret Vision Transformers as ConvNets with Dynamic Convolutions

2023-09-19 · Chong Zhou, Chen Change Loy, Bo Dai

There has been a debate about the superiority between vision Transformers and ConvNets, serving as the backbone of computer vision models. Although they are usually considered as two completely different architectures, i…