paper-with-me

Papers

Image Recognition with Online Lightweight Vision Transformer: A Survey

2025-05-06 · Zherui Zhang, Rongtao Xu, Jie zhou, Changwei Wang, Xingtian Pei, Wenhao Xu, Jiguang Zhang, Li Guo, Longxiang Gao, Wenbo Xu, Shibiao Xu

The Transformer architecture has achieved significant success in natural language processing, motivating its adaptation to computer vision tasks. Unlike convolutional neural networks, vision transformers inherently capture long-range dependencies and enable parallel processing, yet lack inductive biases and efficiency benefits, facing significant computational and memory challenges that limit its real-world applicability. This paper surveys various online strategies for generating lightweight vision transformers for image recognition, focusing on three key areas: Efficient Component Design, Dynamic Network, and Knowledge Distillation. We evaluate the relevant exploration for each topic on the ImageNet-1K benchmark, analyzing trade-offs among precision, parameters, throughput, and more to highlight their respective advantages, disadvantages, and flexibility. Finally, we propose future research directions and potential challenges in the lightweighting of vision transformers with the aim of inspiring further exploration and providing practical guidance for the community. Project Page: https://github.com/ajxklo/Lightweight-VIT

📄 PDF Abstract BibTeX arXiv:2505.03113

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationSurvey

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

MFEViT: A Robust Lightweight Transformer-based Network for Multimodal 2D+3D Facial Expression Recognition

2021-09-20 · Hanting Li, Mingzhe Sui, Zhaoqing Zhu, Feng Zhao

Vision transformer (ViT) has been widely applied in many areas due to its self-attention mechanism that help obtain the global receptive field since the first layer. It even achieves surprising performance exceeding CNN …

3D Facial Expression RecognitionFacial Expression RecognitionFacial Expression Recognition (FER)

VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token Encodings

2025-03-09 · Leonardo Scabini, Kallil M. Zielinski, Emir Konuk, Ricardo T. Fares 외

Texture recognition has recently been dominated by ImageNet-pre-trained deep Convolutional Neural Networks (CNNs), with specialized modifications and feature engineering required to achieve state-of-the-art (SOTA) perfor…

Computational EfficiencyFeature EngineeringTexture Classification

SkelVIT: Consensus of Vision Transformers for a Lightweight Skeleton-Based Action Recognition System

2023-11-14 · Ozge Oztimur Karadag

Skeleton-based action recognition receives the attention of many researchers as it is robust to viewpoint and illumination changes, and its processing is much more efficient than the processing of video frames. With the …

Action RecognitionSkeleton Based Action Recognition

UNIT: Unifying Image and Text Recognition in One Vision Encoder

2024-09-06 · Yi Zhu, Yanpeng Zhou, Chunwei Wang, Yang Cao 외

Currently, vision encoder models like Vision Transformers (ViTs) typically excel at image recognition tasks but cannot simultaneously support text recognition like human visual recognition. To address this limitation, we…

DecoderOptical Character Recognition (OCR)

Part-based Face Recognition with Vision Transformers

2022-11-30 · Zhonglin Sun, Georgios Tzimiropoulos

Holistic methods using CNNs and margin-based losses have dominated research on face recognition. In this work, we depart from this setting in two ways: (a) we employ the Vision Transformer as an architecture for training…

Face Recognition