[NeurIPS'20] Self-supervised Co-Training for Video Representation Learning. Tengda Han, Weidi Xie, Andrew Zisserman.

Last update: Jan 02, 2023

Related tags

Deep Learning CoCLR

Overview

CoCLR: Self-supervised Co-Training for Video Representation Learning

This repository contains the implementation of:

InfoNCE (MoCo on videos)
UberNCE (supervised contrastive learning on videos)
CoCLR

Link:

[Project Page] [PDF] [Arxiv]

News

[2021.01.29] Upload both RGB and optical flow dataset for UCF101 (links).
[2021.01.11] Update our paper for NeurIPS2020 final version: corrected InfoNCE-RGB-linearProbe baseline result in Table1 from 52.3% (pretrained for 800 epochs, unnessary and unfair) to 46.8% (pretrained for 500 epochs, fair comparison). Thanks @liuhualin333 for pointing out.
[2020.12.08] Update instructions.
[2020.11.17] Upload pretrained weights for UCF101 experiments.
[2020.10.30] Update "draft" dataloader files, CoCLR code, evaluation code as requested by some researchers. Will check and add detailed instructions later.

Pretrain Instruction

InfoNCE pretrain on UCF101-RGB

CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch \
--nproc_per_node=2 main_nce.py --net s3d --model infonce --moco-k 2048 \
--dataset ucf101-2clip --seq_len 32 --ds 1 --batch_size 32 \
--epochs 300 --schedule 250 280 -j 16

InfoNCE pretrain on UCF101-Flow

CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch \
--nproc_per_node=2 main_nce.py --net s3d --model infonce --moco-k 2048 \
--dataset ucf101-f-2clip --seq_len 32 --ds 1 --batch_size 32 \
--epochs 300 --schedule 250 280 -j 16

CoCLR pretrain on UCF101 for one cycle

CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch \
--nproc_per_node=2 main_coclr.py --net s3d --topk 5 --moco-k 2048 \
--dataset ucf101-2stream-2clip --seq_len 32 --ds 1 --batch_size 32 \
--epochs 100 --schedule 80 --name_prefix Cycle1-FlowMining_ -j 8 \
--pretrain {rgb_infoNCE_checkpoint.pth.tar} {flow_infoNCE_checkpoint.pth.tar}

CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch \
--nproc_per_node=2 main_coclr.py --net s3d --topk 5 --moco-k 2048 --reverse \
--dataset ucf101-2stream-2clip --seq_len 32 --ds 1 --batch_size 32 \
--epochs 100 --schedule 80 --name_prefix Cycle1-RGBMining_ -j 8 \
--pretrain {flow_infoNCE_checkpoint.pth.tar} {rgb_cycle1_checkpoint.pth.tar}

InfoNCE pretrain on K400-RGB

CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch \
--nproc_per_node=4 main_infonce.py --net s3d --model infonce --moco-k 16384 \
--dataset k400-2clip --lr 1e-3 --seq_len 32 --ds 1 --batch_size 32 \
--epochs 300 --schedule 250 280 -j 16

InfoNCE pretrain on K400-Flow

CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch \
--nproc_per_node=4 teco_fb_main.py --net s3d --model infonce --moco-k 16384 \
--dataset k400-f-2clip --lr 1e-3 --seq_len 32 --ds 1 --batch_size 32 \
--epochs 300 --schedule 250 280 -j 16

CoCLR pretrain on K400 for one cycle

CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch \
--nproc_per_node=2 main_coclr.py --net s3d --topk 5 --moco-k 16384 \
--dataset k400-2stream-2clip --seq_len 32 --ds 1 --batch_size 32 \
--epochs 50 --schedule 40 --name_prefix Cycle1-FlowMining_ -j 8 \
--pretrain {rgb_infoNCE_checkpoint.pth.tar} {flow_infoNCE_checkpoint.pth.tar}

CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch \
--nproc_per_node=2 main_coclr.py --net s3d --topk 5 --moco-k 16384 --reverse \
--dataset k400-2stream-2clip --seq_len 32 --ds 1 --batch_size 32 \
--epochs 50 --schedule 40 --name_prefix Cycle1-RGBMining_ -j 8 \
--pretrain {flow_infoNCE_checkpoint.pth.tar} {rgb_cycle1_checkpoint.pth.tar}

Finetune Instruction

cd eval/ e.g. finetune UCF101-rgb:

CUDA_VISIBLE_DEVICES=0,1 python main_classifier.py --net s3d --dataset ucf101 \
--seq_len 32 --ds 1 --batch_size 32 --train_what ft --epochs 500 --schedule 400 450 \
--pretrain {selected_rgb_pretrained_checkpoint.pth.tar}

then run the test with 10-crop (test-time augmentation is helpful, 10-crop gives better result than center-crop):

CUDA_VISIBLE_DEVICES=0,1 python main_classifier.py --net s3d --dataset ucf101 \
--seq_len 32 --ds 1 --batch_size 32 --train_what ft --epochs 500 --schedule 400 450 \
--test {selected_rgb_finetuned_checkpoint.pth.tar} --ten_crop

Nearest-neighbour Retrieval Instruction

cd eval/ e.g. nn-retrieval for UCF101-rgb

CUDA_VISIBLE_DEVICES=0 python main_classifier.py --net s3d --dataset ucf101 \
--seq_len 32 --ds 1 --test {selected_rgb_pretrained_checkpoint.pth.tar} --retrieval

Linear-probe Instruction

cd eval/

from extracted feature

The code support two methods on linear-probe, either feed the data end-to-end and freeze the backbone, or train linear layer on extracted features. Both methods give similar best results in our experiments.

e.g. on extracted features (after run NN-retrieval command above, features will be saved in os.path.dirname(checkpoint))

CUDA_VISIBLE_DEVICES=0 python feature_linear_probe.py --dataset ucf101 \
--test {feature_dirname} --final_bn --lr 1.0 --wd 1e-3

Note that the default setting should give an alright performance, maybe 1-2% lower than our paper's figure. For different datasets, lr and wd need to be tuned from lr: 0.1 to 1.0; wd: 1e-4 to 1e-1.

load data and freeze backbone

alternatively, feed data end-to-end and freeze the backbone.

CUDA_VISIBLE_DEVICES=0,1 python main_classifier.py --net s3d --dataset ucf101 \
--seq_len 32 --ds 1 --batch_size 32 --train_what last --epochs 100 --schedule 60 80 \
--optim sgd --lr 1e-1 --wd 1e-3 --final_bn --pretrain {selected_rgb_pretrained_checkpoint.pth.tar}

Similarly, lr and wd need to be tuned for different datasets for best performance.

Dataset

RGB for UCF101: [download-from-server] [download-from-gdrive] (tar file, 29GB, packed with lmdb)
TVL1 optical flow for UCF101: [download-from-server] [download-from-gdrive] (tar file, 20.5GB, packed with lmdb)
Note: I created these lmdb files with msgpack==0.6.2, when load them with msgpack>=1.0.0, you can do msgpack.loads(raw_data, raw=True)(issue#32)

Result

Finetune entire network for action classification on UCF101:

Pretrained Weights

Our models:

UCF101-RGB-CoCLR: [download] [[email protected]=51.8 on UCF101-RGB]
UCF101-Flow-CoCLR: [download] [[email protected]=48.4 on UCF101-Flow]

Baseline models:

UCF101-RGB-InfoNCE: [download] [[email protected]=33.1 on UCF101-RGB]
UCF101-Flow-InfoNCE: [download] [[email protected]=45.2 on UCF101-Flow]

Kinetics400-pretrained models：

K400-RGB-CoCLR: [download] [[email protected]=45.6, [email protected]=87.89 on UCF101-RGB]
K400-Flow-CoCLR: [download] [[email protected]=44.4, [email protected]=85.27 on UCF101-Flow]
Two-stream result by average the class probability: 0.8789 + 0.8527 => 0.9061

[NeurIPS'20] Self-supervised Co-Training for Video Representation Learning. Tengda Han, Weidi Xie, Andrew Zisserman.

Related tags

Overview

CoCLR: Self-supervised Co-Training for Video Representation Learning

Link:

News

Pretrain Instruction

Finetune Instruction

Nearest-neighbour Retrieval Instruction

Linear-probe Instruction

from extracted feature

load data and freeze backbone

Dataset

Result

Pretrained Weights

Owner

Tengda Han

SpineAI Bilsky Grading With Python

Memoized coduals - Shows that it is possible to implement reverse mode autodiff using a variation on the dual numbers called the codual numbers

Project page for our ICCV 2021 paper "The Way to my Heart is through Contrastive Learning"

🏃‍♀️ A curated list about human motion capture, analysis and synthesis.

The fastai deep learning library

A python library for implementing a recommender system

GoodNews Everyone! Context driven entity aware captioning for news images

Pytorch implementation of AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks

How to Predict Stock Prices Easily Demo

Source code for TACL paper "KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation".

A Python Library for Graph Outlier Detection (Anomaly Detection)

Pytorch reimplementation of the Mixer (MLP-Mixer: An all-MLP Architecture for Vision)

The implementation of the paper "HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information".

CCCL: Contrastive Cascade Graph Learning.

Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression

Repository for the "Gotta Go Fast When Generating Data with Score-Based Models" paper

Implement of "Training deep neural networks via direct loss minimization" in PyTorch for 0-1 loss

Contenido del curso Bases de datos del DCC PUC versión 2021-2

Accelerate Neural Net Training by Progressively Freezing Layers

[AI6122] Text Data Management & Processing