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

Related tags

Deep LearningELSA
Overview

ELSA: Enhanced Local Self-Attention for Vision Transformer

By Jingkai Zhou, Pichao Wang*, Fan Wang, Qiong Liu, Hao Li, Rong Jin

This repo is the official implementation of "ELSA: Enhanced Local Self-Attention for Vision Transformer".

Introduction

Self-attention is powerful in modeling long-range dependencies, but it is weak in local finer-level feature learning. As shown in Figure 1, the performance of local self-attention (LSA) is just on par with convolution and inferior to dynamic filters, which puzzles researchers on whether to use LSA or its counterparts, which one is better, and what makes LSA mediocre. In this work, we comprehensively investigate LSA and its counterparts. We find that the devil lies in the generation and application of spatial attention.

Based on these findings, we propose the enhanced local self-attention (ELSA) with Hadamard attention and the ghost head, as illustrated in Figure 2. Experiments demonstrate the effectiveness of ELSA. Without architecture / hyperparameter modification, The use of ELSA in drop-in replacement boosts baseline methods consistently in both upstream and downstream tasks.

Please refer to our paper for more details.

Model zoo

ImageNet Classification

Model #Params Pretrain Resolution Top1 Acc Download
ELSA-Swin-T 28M ImageNet 1K 224 82.7 google / baidu
ELSA-Swin-S 53M ImageNet 1K 224 83.5 google / baidu
ELSA-Swin-B 93M ImageNet 1K 224 84.0 google / baidu

COCO Object Detection

Backbone Method Pretrain Lr Schd Box mAP Mask mAP #Params Download
ELSA-Swin-T Mask R-CNN ImageNet-1K 1x 45.7 41.1 49M google / baidu
ELSA-Swin-T Mask R-CNN ImageNet-1K 3x 47.5 42.7 49M google / baidu
ELSA-Swin-S Mask R-CNN ImageNet-1K 1x 48.3 43.0 72M google / baidu
ELSA-Swin-S Mask R-CNN ImageNet-1K 3x 49.2 43.6 72M google / baidu
ELSA-Swin-T Cascade Mask R-CNN ImageNet-1K 1x 49.8 43.0 86M google / baidu
ELSA-Swin-T Cascade Mask R-CNN ImageNet-1K 3x 51.0 44.2 86M google / baidu
ELSA-Swin-S Cascade Mask R-CNN ImageNet-1K 1x 51.6 44.4 110M google / baidu
ELSA-Swin-S Cascade Mask R-CNN ImageNet-1K 3x 52.3 45.2 110M google / baidu

ADE20K Semantic Segmentation

Backbone Method Pretrain Crop Size Lr Schd mIoU (ms+flip) #Params Download
ELSA-Swin-T UPerNet ImageNet-1K 512x512 160K 47.9 61M google / baidu
ELSA-Swin-S UperNet ImageNet-1K 512x512 160K 50.4 85M google / baidu

Install

  • Clone this repo:
git clone https://github.com/damo-cv/ELSA.git elsa
cd elsa
  • Create a conda virtual environment and activate it:
conda create -n elsa python=3.7 -y
conda activate elsa
  • Install PyTorch==1.8.0 and torchvision==0.9.0 with CUDA==10.1:
conda install pytorch==1.8.0 torchvision==0.9.0 cudatoolkit=10.1 -c pytorch
git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./
cd ../
  • Install mmcv-full==1.3.0
pip install mmcv-full==1.3.0 -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.8.0/index.html
  • Install other requirements:
pip install -r requirements.txt
  • Install mmdet and mmseg:
cd ./det
pip install -v -e .
cd ../seg
pip install -v -e .
cd ../
  • Build the elsa operation:
cd ./cls/models/elsa
python setup.py install
mv build/lib*/* .
cp *.so ../../../det/mmdet/models/backbones/elsa/
cp *.so ../../../seg/mmseg/models/backbones/elsa/
cd ../../../

Data preparation

We use standard ImageNet dataset, you can download it from http://image-net.org/. Please prepare it under the following file structure:

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

Also, please prepare the COCO and ADE20K datasets following their links. Then, please link them to det/data and seg/data.

Evaluation

ImageNet Classification

Run following scripts to evaluate pre-trained models on the ImageNet-1K:

cd cls

python validate.py <PATH_TO_IMAGENET> --model elsa_swin_tiny --checkpoint <CHECKPOINT_FILE> \
  --no-test-pool --apex-amp --img-size 224 -b 128

python validate.py <PATH_TO_IMAGENET> --model elsa_swin_small --checkpoint <CHECKPOINT_FILE> \
  --no-test-pool --apex-amp --img-size 224 -b 128

python validate.py <PATH_TO_IMAGENET> --model elsa_swin_base --checkpoint <CHECKPOINT_FILE> \
  --no-test-pool --apex-amp --img-size 224 -b 128 --use-ema

COCO Detection

Run following scripts to evaluate a detector on the COCO:

cd det

# single-gpu testing
python tools/test.py <CONFIG_FILE> <DET_CHECKPOINT_FILE> --eval bbox segm

# multi-gpu testing
tools/dist_test.sh <CONFIG_FILE> <DET_CHECKPOINT_FILE> <GPU_NUM> --eval bbox segm

ADE20K Semantic Segmentation

Run following scripts to evaluate a model on the ADE20K:

cd seg

# single-gpu testing
python tools/test.py <CONFIG_FILE> <SEG_CHECKPOINT_FILE> --aug-test --eval mIoU

# multi-gpu testing
tools/dist_test.sh <CONFIG_FILE> <SEG_CHECKPOINT_FILE> <GPU_NUM> --aug-test --eval mIoU

Training from scratch

Due to randomness, the re-training results may have a gap of about 0.1~0.2% with the numbers in the paper.

ImageNet Classification

Run following scripts to train classifiers on the ImageNet-1K:

cd cls

bash ./distributed_train.sh 8 <PATH_TO_IMAGENET> --model elsa_swin_tiny \
  --epochs 300 -b 128 -j 8 --opt adamw --lr 1e-3 --sched cosine --weight-decay 5e-2 \
  --warmup-epochs 20 --warmup-lr 1e-6 --min-lr 1e-5 --drop-path 0.1 --aa rand-m9-mstd0.5-inc1 \
  --mixup 0.8 --cutmix 1. --remode pixel --reprob 0.25 --clip-grad 5. --amp

bash ./distributed_train.sh 8 <PATH_TO_IMAGENET> --model elsa_swin_small \
  --epochs 300 -b 128 -j 8 --opt adamw --lr 1e-3 --sched cosine --weight-decay 5e-2 \
  --warmup-epochs 20 --warmup-lr 1e-6 --min-lr 1e-5 --drop-path 0.3 --aa rand-m9-mstd0.5-inc1 \
  --mixup 0.8 --cutmix 1. --remode pixel --reprob 0.25 --clip-grad 5. --amp

bash ./distributed_train.sh 8 <PATH_TO_IMAGENET> --model elsa_swin_base \
  --epochs 300 -b 128 -j 8 --opt adamw --lr 1e-3 --sched cosine --weight-decay 5e-2 \
  --warmup-epochs 20 --warmup-lr 1e-6 --min-lr 1e-5 --drop-path 0.5 --aa rand-m9-mstd0.5-inc1 \
  --mixup 0.8 --cutmix 1. --remode pixel --reprob 0.25 --clip-grad 5. --amp --model-ema

If GPU memory is not enough when training elsa_swin_base, you can use two nodes (2 * 8 GPUs), each with a batch size of 64 images/GPU.

COCO Detection / ADE20K Semantic Segmentation

Run following scripts to train models on the COCO / ADE20K:

cd det 
# (or cd seg)

# multi-gpu training
tools/dist_train.sh <CONFIG_FILE> <GPU_NUM> --cfg-options model.pretrained=<PRETRAIN_MODEL> [model.backbone.use_checkpoint=True] [other optional arguments]

Acknowledgement

This work was supported by Alibaba Group through Alibaba Research Intern Program and the National Natural Science Foundation of China (No.61976094).

Codebase from pytorch-image-models, ddfnet, VOLO, Swin-Transformer, Swin-Transformer-Detection, and Swin-Transformer-Semantic-Segmentation

Citing ELSA

@article{zhou2021ELSA,
  title={ELSA: Enhanced Local Self-Attention for Vision Transformer},
  author={Zhou, Jingkai and Wang, Pichao and Wang, Fan and Liu, Qiong and Li, Hao and Jin, Rong},
  journal={arXiv preprint arXiv:2112.12786},
  year={2021}
}
Owner
DamoCV
CV team of DAMO academy
DamoCV
GitHub Repository
Generating Digital Painting Lighting Effects via RGB-space Geometry (SIGGRAPH2020/TOG2020)

Project PaintingLight PaintingLight is a project conducted by the Style2Paints team, aimed at finding a method to manipulate the illumination in digit

651 Dec 29, 2022
NAS Benchmark in "Prioritized Architecture Sampling with Monto-Carlo Tree Search", CVPR2021

NAS-Bench-Macro This repository includes the benchmark and code for NAS-Bench-Macro in paper "Prioritized Architecture Sampling with Monto-Carlo Tree

35 Jan 03, 2023
Semi-supervised Learning for Sentiment Analysis

Neural-Semi-supervised-Learning-for-Text-Classification-Under-Large-Scale-Pretraining Code, models and Datasets for《Neural Semi-supervised Learning fo

47 Jan 01, 2023
Harmonic Memory Networks for Graph Completion

HMemNetworks Code and documentation for Harmonic Memory Networks, a series of models for compositionally assembling representations of graph elements

mlalisse 0 Oct 27, 2021
CNNs for Sentence Classification in PyTorch

Introduction This is the implementation of Kim's Convolutional Neural Networks for Sentence Classification paper in PyTorch. Kim's implementation of t

Shawn Ng 956 Dec 19, 2022
A Deep Learning Framework for Neural Derivative Hedging

NNHedge NNHedge is a PyTorch based framework for Neural Derivative Hedging. The following repository was implemented to ease the experiments of our pa

GUIJIN SON 17 Nov 14, 2022
Official Pytorch and JAX implementation of "Efficient-VDVAE: Less is more"

The Official Pytorch and JAX implementation of "Efficient-VDVAE: Less is more" Arxiv preprint Louay Hazami   ·   Rayhane Mama   ·   Ragavan Thurairatn

Rayhane Mama 144 Dec 23, 2022
A simple Python library for stochastic graphical ecological models

What is Viridicle? Viridicle is a library for simulating stochastic graphical ecological models. It implements the continuous time models described in

Theorem Engine 0 Dec 04, 2021
Non-Imaging Transient Reconstruction And TEmporal Search (NITRATES)

Non-Imaging Transient Reconstruction And TEmporal Search (NITRATES) This repo contains the full NITRATES pipeline for maximum likelihood-driven discov

13 Nov 08, 2022
Official PyTorch implementation for FastDPM, a fast sampling algorithm for diffusion probabilistic models

Official PyTorch implementation for "On Fast Sampling of Diffusion Probabilistic Models". FastDPM generation on CIFAR-10, CelebA, and LSUN datasets. S

Zhifeng Kong 68 Dec 26, 2022
PlaidML is a framework for making deep learning work everywhere.

A platform for making deep learning work everywhere. Documentation | Installation Instructions | Building PlaidML | Contributing | Troubleshooting | R

PlaidML 4.5k Jan 02, 2023
Extreme Dynamic Classifier Chains - XGBoost for Multi-label Classification

Extreme Dynamic Classifier Chains Classifier chains is a key technique in multi-label classification, sinceit allows to consider label dependencies ef

6 Oct 08, 2022
Koç University deep learning framework.

Knet Knet (pronounced "kay-net") is the Koç University deep learning framework implemented in Julia by Deniz Yuret and collaborators. It supports GPU

1.4k Dec 31, 2022
[ICLR 2022] DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

DAB-DETR This is the official pytorch implementation of our ICLR 2022 paper DAB-DETR. Authors: Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi

336 Dec 25, 2022
Code for the paper "Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks"

ON-LSTM This repository contains the code used for word-level language model and unsupervised parsing experiments in Ordered Neurons: Integrating Tree

Yikang Shen 572 Nov 21, 2022
Benchmarks for Object Detection in Aerial Images

Benchmarks for Object Detection in Aerial Images

Jian Ding 691 Dec 30, 2022
Open-Set Recognition: A Good Closed-Set Classifier is All You Need

Open-Set Recognition: A Good Closed-Set Classifier is All You Need Code for our paper: "Open-Set Recognition: A Good Closed-Set Classifier is All You

194 Jan 03, 2023
Unofficial Implementation of RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series (AAAI 2019)

RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series (AAAI 2019) This repository contains python (3.5.2) implementation of

Doyup Lee 222 Dec 21, 2022
A custom DeepStack model that has been trained detecting ONLY the USPS logo

This repository provides a custom DeepStack model that has been trained detecting ONLY the USPS logo. This was created after I discovered that the Deepstack OpenLogo custom model I was using did not

Stephen Stratoti 9 Dec 27, 2022
This repo contains the implementation of YOLOv2 in Keras with Tensorflow backend.

Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower is accessible at https://git.io/vF7vI (not on Windows).

Huynh Ngoc Anh 1.7k Dec 24, 2022