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

Normalization Matters in Weakly Supervised Object Localization (ICCV 2021)

Multi-objective gym environments for reinforcement learning.

MAterial del programa Misión TIC 2022

Controlling a game using mediapipe hand tracking

Official Datasets and Implementation from our Paper "Video Class Agnostic Segmentation in Autonomous Driving".

GEP (GDB Enhanced Prompt) - a GDB plug-in for GDB command prompt with fzf history search, fish-like autosuggestions, auto-completion with floating window, partial string matching in history, and more!

[ACL-IJCNLP 2021] Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning

This project deploys a yolo fastest model in the form of tflite on raspberry 3b+. The model is from another repository of mine called -Trash-Classification-Car

We provided a matlab implementation for an evolutionary multitasking AUC optimization framework (EMTAUC).

R3Det based on mmdet 2.19.0

Implementation of the pix2pix model on satellite images

Tensorflow 2.x implementation of Vision-Transformer model

Recommendationsystem - Movie-recommendation - matrixfactorization colloborative filtering recommendation system user

Deep functional residue identification

Solution of Kaggle competition: Sartorius - Cell Instance Segmentation

An official implementation of "Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation" (ICCV 2021) in PyTorch.

DFM: A Performance Baseline for Deep Feature Matching

QuanTaichi evaluation suite

Source code of "Hold me tight! Influence of discriminative features on deep network boundaries"

Official implementation of "Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision" ECCV2020