DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning

Pytorch Implementation for DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning

If the project is useful to you, please give us a star. ⭐️

@article{gao2021disco,
  title={DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning},
  author={Gao, Yuting and Zhuang, Jia-Xin and Li, Ke and Cheng, Hao and Guo, Xiaowei and Huang, Feiyue and Ji, Rongrong and Sun, Xing},
  journal={arXiv preprint arXiv:2104.09124},
  year={2021}
}

Checkpoints

Teacher Models

Architecture	Self-supervised Methods	Model Checkpoints
ResNet152	MoCo-V2	Model
ResNet101	MoCo-V2	Model
ResNet50	MoCo-V2	Model

For teacher models such as ResNet-50*2 etc, we use their official implementation, which can be downloaded from their github pages.

Student Models by DisCo

Teacher/Students	Efficient-B0	ResNet-18	Vit-Tiny	XCiT-Tiny
ResNet-50	Model	Model	-	-
ResNet-101	Model	Model	-	-
ResNet-152	Model	Model	-	-
ResNet-50*2	Model	Model	-	-
ViT-Small	-	-	Model	-
XCiT-Small	-	-	-	Model

Requirements

Python3
Pytorch 1.6+
Detectron2
8 GPUs are preferred
ImageNet, Cifar10/100, VOC, COCO

Run

Before running, we firstly move all data into share memory

cp /path/to/ImageNet /dev/shm

Pretrain Model

For pretraining baseline models with default hidden layer dimension in Tab1

# Switch to moco directory
cd moco

# R-50
python3 -u main_moco.py -a resnet50 --batch-size 256 --learning-rate 0.03 --mlp --moco-t 0.2 --aug-plus --cos --epochs 200 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --hidden 2048 /dev/shm/ 2>&1 | tee ./logs/std.log
python3 main_lincls.py -a resnet50 --learning-rate 3.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm/ 2>&1 | tee ./logs/std.log

# R-101
python3 -u main_moco.py -a resnet101 --batch-size 256 --learning-rate 0.03 --mlp --moco-t 0.2 --aug-plus --cos --epochs 200 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --hidden 2048 /dev/shm/ 2>&1 | tee ./logs/std.log
python3 main_lincls.py -a resnet101 --learning-rate 3.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm/ 2>&1 | tee ./logs/std.log

# R-152
python3 -u main_moco.py -a resnet152 --batch-size 256 --learning-rate 0.03 --mlp --moco-t 0.2 --aug-plus --cos --epochs 800 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --hidden 2048 /dev/shm/ 2>&1 | tee ./logs/std.log
python3 main_lincls.py -a resnet152 --learning-rate 3.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0799.pth.tar /dev/shm/ 2>&1 | tee ./logs/std.log

# Mob
python3 -u main_moco.py -a mobilenetv3 --batch-size 256 --learning-rate 0.03 --mlp --moco-t 0.2 --aug-plus --cos --epochs 200 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --hidden 512 /dev/shm 2>&1 |  tee ./logs/std.log
#          Evaluation
python3 main_lincls.py -a mobilenetv3 --learning-rate 3.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm/ 2>&1 | tee ./logs/std.log

# Effi-B0
python3 -u main_moco.py -a efficientb0 --batch-size 256 --learning-rate 0.03 --mlp --moco-t 0.2 --aug-plus --cos --epochs 200 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --hidden 1280 2>&1  |  tee ./logs/std.log
#          Evaluation
python3 main_lincls.py -a efficientb0 --learning-rate 3.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm/ 2>&1 | tee ./logs/std.log

# Effi-B1
python3 -u main_moco.py -a efficientb1 --batch-size 256 --learning-rate 0.03 --mlp --moco-t 0.2 --aug-plus --cos --epochs 200 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0  --hidden 1280  /dev/shm  2>&1 | tee ./logs/std.log
#          Evaluation
python3 main_lincls.py -a efficientb1 --learning-rate 3.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm/ 2>&1 | tee ./logs/std.log

# R-18
python3 -u main_moco.py -a resnet18 --batch-size 256 --learning-rate 0.03 --mlp --moco-t 0.2 --aug-plus --cos --epochs 200 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --hidden 1280 /dev/shm/ 2>&1 | tee ./logs/std.log
#          Evaluation
python3 main_lincls.py -a resnet18 --learning-rate 3.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm/ 2>&1 | tee ./logs/std.log

# R-34
python3 -u main_moco.py -a resnet34 --batch-size 256 --learning-rate 0.03 --mlp --moco-t 0.2 --aug-plus --cos --epochs 200 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --hidden 1280 /dev/shm/ 2>&1 | tee ./logs/std.log
#          Evaluation
python3 main_lincls.py -a resnet34 --learning-rate 3.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm/ 2>&1 | tee ./logs/std.log

DisCo

For training DisCo in Tab1, Comparision with baseline

# Switch to DisCo directory
cd DisCo

# R-50 & Effib0
python3 -u main.py -a efficientb0 --lr 0.03 --batch-size 256 --moco-t 0.2 --aug-plus --dist-url 'tcp://localhost:10043' --multiprocessing-distributed --world-size 1 --rank 0 --mlp --cos --teacher_arch resnet50 --teacher /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm/ 2>&1 | tee ./logs/std.log
#          Evaluation
python3 -u main_lincls.py -a efficientb0 --learning-rate 3.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm 2>&1 | tee ./logs/std.log

# R50w2 & Effib0
python3 -u main.py -a efficientb0 --lr 0.03 --batch-size 256 --moco-t 0.2 --aug-plus --dist-url 'tcp://localhost:10043' --multiprocessing-distributed --world-size 1 --rank 0 --mlp --cos --teacher_arch resnet50w2 --teacher /path/to/swav_RN50w2_400ep_pretrain.pth.tar /dev/shm 2>&1 | tee ./logs/std.log
#          Evaluation
python3 yt_main_lincls.py -a resnet18 --learning-rate 30.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar  /dev/shm 2>&1 | tee ./logs/std.log

For Tab2, Linear evaluation top-1 accuracy (%) on ImageNet compared with different distillation methods.

# RKD+DisCo, Eff-b0
python3 -u main_moco_distill_rkd.py -a efficientb0 --lr 0.03 --batch-size 256 --moco-t 0.2 --aug-plus --dist-url 'tcp://localhost:10043' --multiprocessing-distributed --world-size 1 --rank 0 --mlp --cos --teacher /path/to/teacher_res50.pth.tar --use-mse /dev/shm  2>&1 | tee ./logs/std.log
#                  Evaluation
python3 -u main_lincls.py -a efficientb0 --learning-rate 3.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm 2>&1 | tee ./logs/std.log

# RKD, Eff-b0
python3 -u main_moco_distill_rkd.py -a efficientb0 --lr 0.03 --batch-size 256 --moco-t 0.2 --aug-plus --dist-url 'tcp://localhost:10043' --multiprocessing-distributed --world-size 1 --rank 0 --mlp --cos --teacher /path/to/teacher_res50.pth.tar /dev/shm  2>&1 | tee ./logs/std.log
#                  Evaluation
python3 -u main_lincls.py -a efficientb0 --learning-rate 3.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm 2>&1 | tee ./logs/std.log

For Tab3 , **Object detection and instance segmentation results **

# Cp data to /dev/shm and set up path for Detectron2
cp -r /path/to/VOCdevkit/* /dev/shm/
cp -r /path/to/coco_2017 /dev/shm/coco
export DETECTRON2_DATASETS=/dev/shm

pip install /youtu-reid/jiaxzhuang/acmm/detectron2-0.4+cu101-cp36-cp36m-linux_x86_64.whl
cd detection

# Convert model for Detectron2
python3 convert-pretrain-to-detectron2.py /path/ckpt/checkpoint_0199.pth.tar ./output.pkl

# Evaluation on VOC
python3 train_net.py --config-file configs/pascal_voc_R_50_C4_24k_moco.yaml --num-gpus 8 --resume MODEL.RESNETS.DEPTH 34 MODEL.RESNETS.RES2_OUT_CHANNELS 64 2>&1 | tee ../logs/std.log
# Evaluation on CoCo
python3 train_net.py --config-file configs/coco_R_50_C4_2x_moco.yaml --num-gpus 8  --resume MODEL.RESNETS.DEPTH 18 MODEL.RESNETS.RES2_OUT_CHANNELS 64 2>&1 | tee ../logs/std.log

For Fig5 , evaluation on Semi-Supervised Tasks

# Copy 1%, 10% ImageNet from the complete ImageNet, according to split from SimCLR.
cd data
# Need to set up path to Compelete ImageNet and the output path.
python3 -u imagenet_1_fraction.py --ratio 1
python3 -u imagenet_1_fraction.py --ratio 10

# Evaluation on 1% ImageNet with Eff-B0 by DisCo
cp -r /path/to/imagenet_1_fraction/train  /dev/shm
cp -r /path/to/imagenet_1_fraction/val  /dev/shm/
python3 -u main_lincls_semi.py -a efficientb0 --learning-rate 3.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm  2>&1 | tee ./logs/std.log

# Evaluation on 10% ImageNet with R-18 by DisCo
cp -r /path/to/imagenet_10_fraction/train  /dev/shm
cp -r /path/to/imagenet_10_fraction/val  /dev/shm/
python3 -u main_lincls_semi.py -a resnet18 --learning-rate 3.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm  2>&1 | tee ./logs/std.log

For Fig6, evaluation on Cifar10/Cifar100

# Copy Cifar10/100 to /dev/shm
cp /path/to/Cifar10/100 /dev/shm

# Evaluation on 1% Cifar10 with Eff-B0 by DisCo
python3 cifar_main_lincls.py -a efficientb0 --dataset cifar10 --lr 3 --epochs 200 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm 2>&1 | tee ./logs/std.log
# Evaluation on  Cifar100 with Resnet18 by DisCo
python3 cifar_main_lincls.py -a resnet18 --dataset cifar100 --lr 3 --epochs 200 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm 2>&1 | tee ./logs/std.log

For Tab4, Linear evaluation top-1 accuracy (%) on ImageNet, compared with SEED with consistent dimension in hidden layer.

python3 -u main.py -a efficientb0 --lr 0.03 --batch-size 256 --moco-t 0.2 --aug-plus --dist-url 'tcp://localhost:10043' --multiprocessing-distributed --world-size 1 --rank 0 --mlp --cos --teacher_arch resnet50 --teacher /path/to/ckpt/checkpoint_0199.pth.tar --hidden 2048 /dev/shm/ 2>&1 | tee ./logs/std.log
#          Evaluation
python3 -u main_lincls.py -a efficientb0 --learning-rate 3.0 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 --pretrained /path/to/ckpt/checkpoint_0199.pth.tar /dev/shm 2>&1 | tee ./logs/std.log

For Tab5, Linear evaluation top-1 accuracy (%) on ImageNet with SwAV as the testbed.

# SwAV, Train with SwAV only
cd swav-master
python3 -m torch.distributed.launch --nproc_per_node=8 main_swav.py \
        --data_path /dev/shm/train \
        --base_lr 0.6 \
        --final_lr 0.0006 \
        --warmup_epochs 0 \
        --crops_for_assign 0 1 \
        --size_crops 224 96 \
        --nmb_crops 2 6 \
        --min_scale_crops 0.14 0.05 \
        --max_scale_crops 1. 0.14 \
        --use_fp16 true \
        --freeze_prototypes_niters 5005 \
        --queue_length 3840 \
        --epoch_queue_starts 15 \
        --dump_path ./ckpt \
        --sync_bn pytorch \
        --temperature 0.1 \
        --epsilon 0.05 \
        --sinkhorn_iterations 3 \
        --feat_dim 128 \
        --nmb_prototypes 3000 \
        --epochs 200 \
        --batch_size 64 \
        --wd 0.000001 \
        --arch efficientb0 \
        --use_fp16 true 2>&1 | tee ./logs/std.log
# Evaluation
python3 -m torch.distributed.launch --nproc_per_node=8 eval_linear.py --arch efficientb0 --data_path /dev/shm --pretrained /path/to/ckpt/checkpoints/ckp-199.pth 2>&1 | tee ./logs/std.log

# DisCo + SwAV
python3 -m torch.distributed.launch --nproc_per_node=8 main_swav_distill.py \
        --data_path /dev/shm/train \
        --base_lr 0.6 \
        --final_lr 0.0006 \
        --warmup_epochs 0 \
        --crops_for_assign 0 1 \
        --size_crops 224 96 \
        --nmb_crops 2 6 \
        --min_scale_crops 0.14 0.05 \
        --max_scale_crops 1. 0.14 \
        --use_fp16 true \
        --freeze_prototypes_niters 5005 \
        --queue_length 3840 \
        --epoch_queue_starts 15 \
        --dump_path ./ckpt \
        --sync_bn pytorch \
        --temperature 0.1 \
        --epsilon 0.05 \
        --sinkhorn_iterations 3 \
        --feat_dim 128 \
        --nmb_prototypes 3000 \
        --epochs 200 \
        --batch_size 64 \
        --wd 0.000001 \
        --arch efficientb0 \
        --pretrained /path/to/swav_800ep_pretrain.pth.tar 2>&1 | tee ./logs/std.log

For Tab6, Linear evaluation top-1 accuracy (%) on ImageNet with variants of teacher pre-training methods.

# SwAV
python3 -u main.py -a resnet34 --lr 0.03 --batch-size 256 --moco-t 0.2 --aug-plus --dist-url 'tcp://localhost:10043' --multiprocessing-distributed --world-size 1 --rank 0 --mlp --cos --teacher_arch SWAVresnet50 --teacher /path/to/swav_800ep_pretrain.pth.tar /dev/shm 2>&1 | tee ./logs/std.log

Visualization

cd DisCo
# Generate Embed
# Move Embed to data path

python -u draw.py

Thanks

Code heavily depends on MoCo-V2, Detectron2.

Code for DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning

Related tags

Overview

DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning

If the project is useful to you, please give us a star. ⭐️

Checkpoints

Teacher Models

Student Models by DisCo

Requirements

Run

Pretrain Model

DisCo

Visualization

Thanks

Owner

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

A Fast Monotone Rotating Shallow Water model

Source code for our EMNLP'21 paper 《Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning》

Data and code for the paper "Importance of Kernel Bandwidth in Quantum Machine Learning"

GNN4Traffic - This is the repository for the collection of Graph Neural Network for Traffic Forecasting

Exploring Relational Context for Multi-Task Dense Prediction [ICCV 2021]

AI-generated-characters for Learning and Wellbeing

PyMove is a Python library to simplify queries and visualization of trajectories and other spatial-temporal data

This repository contains a PyTorch implementation of "AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis".

Code for STFT Transformer used in BirdCLEF 2021 competition.

Automated detection of anomalous exoplanet transits in light curve data.

Toward Spatially Unbiased Generative Models (ICCV 2021)

Isaac Gym Reinforcement Learning Environments

A PyTorch Implementation of "SINE: Scalable Incomplete Network Embedding" (ICDM 2018).

Torch implementation of "Enhanced Deep Residual Networks for Single Image Super-Resolution"

Investigating Attention Mechanism in 3D Point Cloud Object Detection (arXiv 2021)

上海交通大学全自动抢课脚本，支持准点开抢与抢课后持续捡漏两种模式。2021/06/08更新。

This repository contains the code for the paper Neural RGB-D Surface Reconstruction

The NEOSSat is a dual-mission microsatellite designed to detect potentially hazardous Earth-orbit-crossing asteroids and track objects that reside in deep space

PyTorch reimplementation of the Smooth ReLU activation function proposed in the paper "Real World Large Scale Recommendation Systems Reproducibility and Smooth Activations" [arXiv 2022].