Official PyTorch implementation of Less is More: Pay Less Attention in Vision Transformers.

Overview

Less is More: Pay Less Attention in Vision Transformers

Official PyTorch implementation of Less is More: Pay Less Attention in Vision Transformers.

By Zizheng Pan, Bohan Zhuang, Haoyu He, Jing Liu and Jianfei Cai.

In our paper, we present a novel Less attention vIsion Transformer (LIT), building upon the fact that convolutions, fully-connected (FC) layers, and self-attentions have almost equivalent mathematical expressions for processing image patch sequences. LIT uses pure multi-layer perceptrons (MLPs) to encode rich local patterns in the early stages while applying self-attention modules to capture longer dependencies in deeper layers. Moreover, we further propose a learned deformable token merging module to adaptively fuse informative patches in a non-uniform manner.

If you use this code for a paper please cite:

@article{pan2021less,
  title={Less is More: Pay Less Attention in Vision Transformers},
  author={Pan, Zizheng and Zhuang, Bohan and He, Haoyu and Liu, Jing and Cai, Jianfei},
  journal={arXiv preprint arXiv:2105.14217},
  year={2021}
}

Usage

First, clone this repository.

git clone https://github.com/MonashAI/LIT

Next, create a conda virtual environment.

# Make sure you have a NVIDIA GPU.
cd LIT/
bash setup_env.sh [conda_install_path] [env_name]

# For example
bash setup_env.sh /home/anaconda3 lit

Note: We use PyTorch 1.7.1 with CUDA 10.1 for all experiments. The setup_env.sh has illustrated all dependencies we used in our experiments. You may want to edit this file to install a different version of PyTorch or any other packages.

Data Preparation

Download the ImageNet 2012 dataset from here, and prepare the dataset based on this script. The file structure should look like:

imagenet
├── train
│   ├── class1
│   │   ├── img1.jpeg
│   │   ├── img2.jpeg
│   │   └── ...
│   ├── class2
│   │   ├── img3.jpeg
│   │   └── ...
│   └── ...
└── val
    ├── class1
    │   ├── img4.jpeg
    │   ├── img5.jpeg
    │   └── ...
    ├── class2
    │   ├── img6.jpeg
    │   └── ...
    └── ...

Model Zoo

We provide baseline LIT models pretrained on ImageNet 2012.

Name Params (M) FLOPs (G) Top-1 Acc. (%) Model Log
LIT-Ti 19 3.6 81.1 google drive/github log
LIT-S 27 4.1 81.5 google drive/github log
LIT-M 48 8.6 83.0 google drive/github log
LIT-B 86 15.0 83.4 google drive/github log

Training and Evaluation

In our implementation, we have different training strategies for LIT-Ti and other LIT models. Therefore, we provide two codebases.

For LIT-Ti, please refer to code_for_lit_ti.

For LIT-S, LIT-M, LIT-B, please refer to code_for_lit_s_m_b.

License

This repository is released under the Apache 2.0 license as found in the LICENSE file.

Acknowledgement

This repository has adopted codes from DeiT, PVT and Swin, we thank the authors for their open-sourced code.

You might also like...
This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.

Introduction This is an official implementation of CvT: Introducing Convolutions to Vision Transformers. We present a new architecture, named Convolut

Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention

cosFormer Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention Update log 2022/2/28 Add core code License This

Official implementation of CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification

CrossViT This repository is the official implementation of CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification. ArXiv If

The official implementation of ELSA: Enhanced Local Self-Attention for Vision Transformer
The official implementation of ELSA: Enhanced Local Self-Attention for Vision Transformer

ELSA: Enhanced Local Self-Attention for Vision Transformer By Jingkai Zhou, Pich

Implementation of SE3-Transformers for Equivariant Self-Attention, in Pytorch.

SE3 Transformer - Pytorch Implementation of SE3-Transformers for Equivariant Self-Attention, in Pytorch. May be needed for replicating Alphafold2 resu

Pytorch implementation for  our ICCV 2021 paper
Pytorch implementation for our ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering".

TRAnsformer Routing Networks (TRAR) This is an official implementation for ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visu

PyTorch Implementation of CvT: Introducing Convolutions to Vision Transformers
PyTorch Implementation of CvT: Introducing Convolutions to Vision Transformers

CvT: Introducing Convolutions to Vision Transformers Pytorch implementation of CvT: Introducing Convolutions to Vision Transformers Usage: img = torch

A PyTorch implementation of ViTGAN based on paper ViTGAN: Training GANs with Vision Transformers.
A PyTorch implementation of ViTGAN based on paper ViTGAN: Training GANs with Vision Transformers.

ViTGAN: Training GANs with Vision Transformers A PyTorch implementation of ViTGAN based on paper ViTGAN: Training GANs with Vision Transformers. Refer

Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image classification, in Pytorch
Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image classification, in Pytorch

Transformer in Transformer Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image c

Comments
  • Problem about DCN

    Problem about DCN

    I have some problems about compiling DCN, thus it is hard for me to use the DCN.deform_conv2d_forward and DCN.deform_conv2d_backward functions. Can 'deform_conv2d_naive' be used instead of this part? Or is there other methods for me to accomplish this DCN.deform_conv2d part?

    opened by jarygrace 3
  • How to use LITNet as a beckbone of object detection

    How to use LITNet as a beckbone of object detection

    Could you please release the code of using LITNet as a beckbone of RetinaNet as mentioned in your paper? I wonder how to use it as a beckbone for object detection...

    opened by sunhuisunhui 2
A python tutorial on bayesian modeling techniques (PyMC3)

Bayesian Modelling in Python Welcome to "Bayesian Modelling in Python" - a tutorial for those interested in learning how to apply bayesian modelling t

Mark Regan 2.4k Jan 06, 2023
Mercer Gaussian Process (MGP) and Fourier Gaussian Process (FGP) Regression

Mercer Gaussian Process (MGP) and Fourier Gaussian Process (FGP) Regression We provide the code used in our paper "How Good are Low-Rank Approximation

Aristeidis (Ares) Panos 0 Dec 13, 2021
Lava-DL, but with PyTorch-Lightning flavour

Deep learning project seed Use this seed to start new deep learning / ML projects. Built in setup.py Built in requirements Examples with MNIST Badges

Sami BARCHID 4 Oct 31, 2022
Generic Event Boundary Detection: A Benchmark for Event Segmentation

Generic Event Boundary Detection: A Benchmark for Event Segmentation We release our data annotation & baseline codes for detecting generic event bound

47 Nov 22, 2022
Hyperbolic Hierarchical Clustering.

Hyperbolic Hierarchical Clustering (HypHC) This code is the official PyTorch implementation of the NeurIPS 2020 paper: From Trees to Continuous Embedd

HazyResearch 154 Dec 15, 2022
EM-POSE 3D Human Pose Estimation from Sparse Electromagnetic Trackers.

EM-POSE: 3D Human Pose Estimation from Sparse Electromagnetic Trackers This repository contains the code to our paper published at ICCV 2021. For ques

Facebook Research 62 Dec 14, 2022
AITom is an open-source platform for AI driven cellular electron cryo-tomography analysis.

AITom Introduction AITom is an open-source platform for AI driven cellular electron cryo-tomography analysis. AITom is originated from the tomominer l

93 Jan 02, 2023
A deep learning model for style-specific music generation.

DeepJ: A model for style-specific music generation https://arxiv.org/abs/1801.00887 Abstract Recent advances in deep neural networks have enabled algo

Henry Mao 704 Nov 23, 2022
Technical Analysis library in pandas for backtesting algotrading and quantitative analysis

bta-lib - A pandas based Technical Analysis Library bta-lib is pandas based technical analysis library and part of the backtrader family. Links Main P

DRo 393 Dec 20, 2022
Kaggle Feedback Prize - Evaluating Student Writing 15th solution

Kaggle Feedback Prize - Evaluating Student Writing 15th solution First of all, I would like to thank the excellent notebooks and discussions from http

Lingyuan Zhang 6 Mar 24, 2022
SHIFT15M: multiobjective large-scale fashion dataset with distributional shifts

[arXiv] The main motivation of the SHIFT15M project is to provide a dataset that contains natural dataset shifts collected from a web service IQON, wh

ZOZO, Inc. 138 Nov 24, 2022
Official repository of the AAAI'2022 paper "Contrast and Generation Make BART a Good Dialogue Emotion Recognizer"

CoG-BART Contrast and Generation Make BART a Good Dialogue Emotion Recognizer Quick Start: To run the model on test sets of four datasets, Download th

39 Dec 24, 2022
Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two

512x512 flowers after 12 hours of training, 1 gpu 256x256 flowers after 12 hours of training, 1 gpu Pizza 'Lightweight' GAN Implementation of 'lightwe

Phil Wang 1.5k Jan 02, 2023
Optimizing DR with hard negatives and achieving SOTA first-stage retrieval performance on TREC DL Track (SIGIR 2021 Full Paper).

Optimizing Dense Retrieval Model Training with Hard Negatives Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, Shaoping Ma 🔥 News 2021-10

Jingtao Zhan 99 Dec 27, 2022
HTSeq is a Python library to facilitate processing and analysis of data from high-throughput sequencing (HTS) experiments.

HTSeq DEVS: https://github.com/htseq/htseq DOCS: https://htseq.readthedocs.io A Python library to facilitate programmatic analysis of data from high-t

HTSeq 57 Dec 20, 2022
Bayesian Neural Networks in PyTorch

We present the new scheme to compute Monte Carlo estimator in Bayesian VI settings with almost no memory cost in GPU, regardles of the number of sampl

Jurijs Nazarovs 7 May 03, 2022
Oscar and VinVL

Oscar: Object-Semantics Aligned Pre-training for Vision-and-Language Tasks VinVL: Revisiting Visual Representations in Vision-Language Models Updates

Microsoft 938 Dec 26, 2022
For encoding a text longer than 512 tokens, for example 800. Set max_pos to 800 during both preprocessing and training.

LongScientificFormer For encoding a text longer than 512 tokens, for example 800. Set max_pos to 800 during both preprocessing and training. Some code

Athar Sefid 6 Nov 02, 2022
DTCN IJCAI - Sequential prediction learning framework and algorithm

DTCN This is the implementation of our paper "Sequential Prediction of Social Me

Bobby 2 Jan 24, 2022
Python scripts for performing stereo depth estimation using the MobileStereoNet model in ONNX

ONNX-MobileStereoNet Python scripts for performing stereo depth estimation using the MobileStereoNet model in ONNX Stereo depth estimation on the cone

Ibai Gorordo 23 Nov 29, 2022