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

Install CUDA==10.1 with cudnn7 following the official installation instructions
Install Apex:

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}
}

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

Related tags

Overview

ELSA: Enhanced Local Self-Attention for Vision Transformer

Introduction

Model zoo

ImageNet Classification

COCO Object Detection

ADE20K Semantic Segmentation

Install

Data preparation

Evaluation

ImageNet Classification

COCO Detection

ADE20K Semantic Segmentation

Training from scratch

ImageNet Classification

COCO Detection / ADE20K Semantic Segmentation

Acknowledgement

Citing ELSA

Owner

DamoCV

gtfs2vec - Learning GTFS Embeddings for comparing PublicTransport Offer in Microregions

NER for Indian languages

Deep Learning for Time Series Forecasting.

GalaXC: Graph Neural Networks with Labelwise Attention for Extreme Classification

A simple editor for captions in .SRT file extension

Human pose estimation from video plays a critical role in various applications such as quantifying physical exercises, sign language recognition, and full-body gesture control.

FAMIE is a comprehensive and efficient active learning (AL) toolkit for multilingual information extraction (IE)

Non-Vacuous Generalisation Bounds for Shallow Neural Networks

A spherical CNN for weather forecasting

A customisable game where you have to quickly click on black tiles in order of appearance while avoiding clicking on white squares.

A small library of 3D related utilities used in my research.

Hyperparameters tuning and features selection are two common steps in every machine learning pipeline.

We present a framework for training multi-modal deep learning models on unlabelled video data by forcing the network to learn invariances to transformations applied to both the audio and video streams.

Diverse Object-Scene Compositions For Zero-Shot Action Recognition

Official code for Score-Based Generative Modeling through Stochastic Differential Equations

Deep learning image registration library for PyTorch

Vertex AI: Serverless framework for MLOPs (ESP / ENG)

Riemannian Convex Potential Maps

Advanced yabai wooting scripts

The implementation of the algorithm in the paper "Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data" published in ICML 2020.