So-ViT: Mind Visual Tokens for Vision Transformer

Related tags

Deep LearningSo-ViT
Overview

So-ViT: Mind Visual Tokens for Vision Transformer

      

Introduction

This repository contains the source code under PyTorch framework and models trained on ImageNet-1K dataset for the following paper:

@articles{So-ViT,
    author = {Jiangtao Xie, Ruiren Zeng, Qilong Wang, Ziqi Zhou, Peihua Li},
    title = {So-ViT: Mind Visual Tokens for Vision Transformer},
    booktitle = {arXiv:2104.10935},
    year = {2021}
}

The Vision Transformer (ViT) heavily depends on pretraining using ultra large-scale datasets (e.g. ImageNet-21K or JFT-300M) to achieve high performance, while significantly underperforming on ImageNet-1K if trained from scratch. We propose a novel So-ViT model toward addressing this problem, by carefully considering the role of visual tokens.

Above all, for classification head, the ViT only exploits class token while entirely neglecting rich semantic information inherent in high-level visual tokens. Therefore, we propose a new classification paradigm, where the second-order, cross-covariance pooling of visual tokens is combined with class token for final classification. Meanwhile, a fast singular value power normalization is proposed for improving the second-order pooling.

Second, the ViT employs the naïve method of one linear projection of fixed-size image patches for visual token embedding, lacking the ability to model translation equivariance and locality. To alleviate this problem, we develop a light-weight, hierarchical module based on off-the-shelf convolutions for visual token embedding.

Classification results

Classification results (single crop 224x224, %) on ImageNet-1K validation set

Network Top-1 Accuracy Pre-trained models
Paper reported Upgrade GoogleDrive BaiduCloud
So-ViT-7 76.2 76.8 Coming soon Coming soon
So-ViT-10 77.9 78.7 Coming soon Coming soon
So-ViT-14 81.8 82.3 Coming soon Coming soon
So-ViT-19 82.4 82.8 Coming soon Coming soon

Installation and Usage

  1. Install PyTorch (>=1.6.0)
  2. Install timm (==0.3.4)
  3. pip install thop
  4. type git clone https://github.com/jiangtaoxie/So-ViT
  5. prepare the dataset as follows
.
├── train
│   ├── class1
│   │   ├── class1_001.jpg
│   │   ├── class1_002.jpg
|   |   └── ...
│   ├── class2
│   ├── class3
│   ├── ...
│   ├── ...
│   └── classN
└── val
    ├── class1
    │   ├── class1_001.jpg
    │   ├── class1_002.jpg
    |   └── ...
    ├── class2
    ├── class3
    ├── ...
    ├── ...
    └── classN

for training from scracth

sh model_name.sh  # model_name = {So_vit_7/10/14/19}

Acknowledgment

pytorch: https://github.com/pytorch/pytorch

timm: https://github.com/rwightman/pytorch-image-models

T2T-ViT: https://github.com/yitu-opensource/T2T-ViT

Contact

If you have any questions or suggestions, please contact me

[email protected]

Owner
Jiangtao Xie
Jiangtao Xie
STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech

STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech Keon Lee, Ky

Keon Lee 114 Dec 12, 2022
LSTM Neural Networks for Spectroscopic Studies of Type Ia Supernovae

Package Description The difficulties in acquiring spectroscopic data have been a major challenge for supernova surveys. snlstm is developed to provide

7 Oct 11, 2022
EXplainable Artificial Intelligence (XAI)

EXplainable Artificial Intelligence (XAI) This repository includes the codes for different projects on eXplainable Artificial Intelligence (XAI) by th

4 Nov 28, 2022
Text Extraction Formulation + Feedback Loop for state-of-the-art WSD (EMNLP 2021)

ConSeC is a novel approach to Word Sense Disambiguation (WSD), accepted at EMNLP 2021. It frames WSD as a text extraction task and features a feedback loop strategy that allows the disambiguation of

Sapienza NLP group 36 Dec 13, 2022
Megaverse is a new 3D simulation platform for reinforcement learning and embodied AI research

Megaverse Megaverse is a new 3D simulation platform for reinforcement learning and embodied AI research. The efficient design of the engine enables ph

Aleksei Petrenko 191 Dec 23, 2022
YoloAll is a collection of yolo all versions. you you use YoloAll to test yolov3/yolov5/yolox/yolo_fastest

官方讨论群 QQ群:552703875 微信群:15158106211(先加作者微信,再邀请入群) YoloAll项目简介 YoloAll是一个将当前主流Yolo版本集成到同一个UI界面下的推理预测工具。可以迅速切换不同的yolo版本,并且可以针对图片,视频,摄像头码流进行实时推理,可以很方便,直观

DL-Practise 244 Jan 01, 2023
Large-Scale Unsupervised Object Discovery

Large-Scale Unsupervised Object Discovery Huy V. Vo, Elena Sizikova, Cordelia Schmid, Patrick Pérez, Jean Ponce [PDF] We propose a novel ranking-based

17 Sep 19, 2022
Implementation of EMNLP 2017 Paper "Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog" using PyTorch and ParlAI

Language Emergence in Multi Agent Dialog Code for the Paper Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog Satwik Kottur, José M.

Karan Desai 105 Nov 25, 2022
Official implementation of Pixel-Level Bijective Matching for Video Object Segmentation

BMVOS This is the official implementation of Pixel-Level Bijective Matching for Video Object Segmentation, to appear in WACV 2022. @article{cho2021pix

Suhwan Cho 13 Dec 14, 2022
BARTScore: Evaluating Generated Text as Text Generation

This is the Repo for the paper: BARTScore: Evaluating Generated Text as Text Generation Updates 2021.06.28 Release online evaluation Demo 2021.06.25 R

NeuLab 196 Dec 17, 2022
[EMNLP 2021] MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations

MuVER This repo contains the code and pre-trained model for our EMNLP 2021 paper: MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity

24 May 30, 2022
https://arxiv.org/abs/2102.11005

LogME LogME: Practical Assessment of Pre-trained Models for Transfer Learning How to use Just feed the features f and labels y to the function, and yo

THUML: Machine Learning Group @ THSS 149 Dec 19, 2022
Learning Synthetic Environments and Reward Networks for Reinforcement Learning

Learning Synthetic Environments and Reward Networks for Reinforcement Learning We explore meta-learning agent-agnostic neural Synthetic Environments (

AutoML-Freiburg-Hannover 16 Sep 02, 2022
A package, and script, to perform imaging transcriptomics on a neuroimaging scan.

Imaging Transcriptomics Imaging transcriptomics is a methodology that allows to identify patterns of correlation between gene expression and some prop

Alessio Giacomel 10 Dec 27, 2022
ManipulaTHOR, a framework that facilitates visual manipulation of objects using a robotic arm

ManipulaTHOR: A Framework for Visual Object Manipulation Kiana Ehsani, Winson Han, Alvaro Herrasti, Eli VanderBilt, Luca Weihs, Eric Kolve, Aniruddha

AI2 65 Dec 30, 2022
[SDM 2022] Towards Similarity-Aware Time-Series Classification

SimTSC This is the PyTorch implementation of SDM2022 paper Towards Similarity-Aware Time-Series Classification. We propose Similarity-Aware Time-Serie

Daochen Zha 49 Dec 27, 2022
A commany has recently introduced a new type of bidding, the average bidding, as an alternative to the bid given to the current maximum bidding

Business Problem A commany has recently introduced a new type of bidding, the average bidding, as an alternative to the bid given to the current maxim

Kübra Bilinmiş 1 Jan 15, 2022
Large scale PTM - PPI relation extraction

Large-scale protein-protein post-translational modification extraction with distant supervision and confidence calibrated BioBERT The silver standard

1 Feb 25, 2022
Generating retro pixel game characters with Generative Adversarial Networks. Dataset "TinyHero" included.

pixel_character_generator Generating retro pixel game characters with Generative Adversarial Networks. Dataset "TinyHero" included. Dataset TinyHero D

Agnieszka Mikołajczyk 88 Nov 17, 2022
object recognition with machine learning on Respberry pi

Respberrypi_object-recognition object recognition with machine learning on Respberry pi line.py 建立一支與樹梅派連線的 linebot 使用此 linebot 遠端控制樹梅派拍照 config.ini l

1 Dec 11, 2021