Code release for NeurIPS 2020 paper "Co-Tuning for Transfer Learning"

THUML @ Tsinghua University

Last update: Sep 23, 2022

Related tags

Deep Learning CoTuning

Overview

CoTuning

Official implementation for NeurIPS 2020 paper Co-Tuning for Transfer Learning.

[News] 2021/01/13 The COCO 70 dataset used in the paper is available for download!

COCO 70 dataset

COCO 70 dataset is a large-scale classification dataset (1000 images per class) created from COCO. It is used to explore the effect of fine-tuning with a large amount of data. Check our paper if you are interested in how it was created. Please respect the original license of COCO when you use it.

To download COCO 70, follow these steps:

download separate files here (the file is too large to upload, so I have to split it into chunks)
merge separate files into a single file by cat COCO70_splita* > COCO70.tar
extract the dataset from the file by tar -xf COCO70.tar

The directory architecture looks like the following:

├── classes.txt #per class name per name

├── dev

├── dev.txt # [filename, class_index] per line, 0 <= class_index <= 69

├── test

├── test.txt

├── train

└── train.txt

There are 100 images per class for validation (dev.txt) and test (test.txt) respectively, and 800 images per class for training (train.txt).

Dependencies

python3
torch == 1.1.0 (with suitable CUDA and CuDNN version)
torchvision == 0.3.0
scikit-learn
numpy
argparse
tqdm

Datasets

Dataset	Download Link
CUB-200-2011	http://www.vision.caltech.edu/visipedia/CUB-200-2011.html
Stanford Cars	http://ai.stanford.edu/~jkrause/cars/car_dataset.html
FGVC Aircraft	http://www.robots.ox.ac.uk/~vgg/data/fgvc-aircraft/

Quick Start

python --gpu [gpu_num] --data_path /path/to/dataset --class_num [class_num] --trade_off 2.3 train.py

Citation

If you use our code or use the constructed COCO-70 dataset, please consider citing:

@article{you2020co,
  title={Co-Tuning for Transfer Learning},
  author={You, Kaichao and Kou, Zhi and Long, Mingsheng and Wang, Jianmin},
  journal={Advances in Neural Information Processing Systems},
  volume={33},
  year={2020}
}

Contact

If you have any problem about our code, feel free to contact [email protected] or [email protected].

Code release for the ICML 2021 paper "PixelTransformer: Sample Conditioned Signal Generation".

PixelTransformer Code release for the ICML 2021 paper "PixelTransformer: Sample Conditioned Signal Generation". Project Page Installation Please insta

24 Dec 17, 2022

Code release for ICCV 2021 paper "Anticipative Video Transformer"

Anticipative Video Transformer Ranked first in the Action Anticipation task of the CVPR 2021 EPIC-Kitchens Challenge! (entry: AVT-FB-UT) [project page

123 Dec 13, 2022

Official code release for ICCV 2021 paper SNARF: Differentiable Forward Skinning for Animating Non-rigid Neural Implicit Shapes.

235 Dec 26, 2022

This repo is the code release of EMNLP 2021 conference paper "Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories".

Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories This repo is the code release of EMNLP 2021 con

12 Nov 22, 2022

The code release of paper Low-Light Image Enhancement with Normalizing Flow

[AAAI 2022] Low-Light Image Enhancement with Normalizing Flow Paper | Project Page Low-Light Image Enhancement with Normalizing Flow Yufei Wang, Renji

176 Jan 6, 2023

UDP++ (ECCVW 2020 Oral), (Winner of COCO 2020 Keypoint Challenge).

UDP-Pose This is the pytorch implementation for UDP++, which won the Fisrt place in COCO Keypoint Challenge at ECCV 2020 Workshop. Top-Down Results on

20 Jul 29, 2022

Code for paper ECCV 2020 paper: Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop.

Who Left the Dogs Out? Evaluation and demo code for our ECCV 2020 paper: Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization

29 Dec 28, 2022

git《Beta R-CNN: Looking into Pedestrian Detection from Another Perspective》(NeurIPS 2020) GitHub:[fig3]

Beta R-CNN: Looking into Pedestrian Detection from Another Perspective This is the pytorch implementation of our paper "[Beta R-CNN: Looking into Pede

35 Sep 8, 2021

Official implementation of "GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators" (NeurIPS 2020)

GS-WGAN This repository contains the implementation for GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators (NeurIPS

46 Nov 9, 2022

Comments

CoTuning execution result problem

My environment :

CUDA 10.1
python 3.7.10
pytorch == 1.7.1
torchvision == 0.8.2
torchaudio == 0.7.2
scikit-learn == 0.24.1
numpy == 1.20.1
argparse == 1.4.0 
tqdm == 4.59.0

Dataset Downloadlink : https://drive.google.com/file/d/1hbzc_P1FuxMkcabkgn9ZKinBwW683j45/view

Offical CUB-200-2011 dataset ( 001. ~ 200. )

My CUB-200-2011 dataset directory architecture :

CoTung
├── data/
│   └── finetune/ 
│       └── cub200/ 
│           ├── test/
│           │   └── test/
│           │       └── ... (151. ~ 200. image folder)
│           ├── train/
│           │   └── train/
│           │       └── ... (001. ~ 120. image folder)
│           └──  val/
│               └── val/
│                   └── ... (121. ~ 150. image folder)
├── module/
├── train.py
└── ...

My Quick Start :

$ python train.py --gpu 0 --data_path ./data/finetune/cub200/ --class_num 200 --batch_size 32

Result :

How to solve ? Thanks !

opened by sksksk1748 5

How to determine the number of iter？

Very nice job! I wonder how to determine the number of iteraitons to better reproduce the result. Is it determined according to the size of the data set and the fixed number of epochs? Thank you very much ！

opened by shihaobai 2
Reproducibility issue

Do you mind sharing the exact split for each dataset for reproducibility? It would be nice if you can tar the file and put it in a drive for download. While you have roughly specified the architecture and the data splitting for COCO dataset, the data splittings for other datasets are not provided. Thanks in advance.

opened by korawat-tanwisuth 1

Owner

THUML @ Tsinghua University

Machine Learning Group, School of Software, Tsinghua University

GitHub

This is the official repo for TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations at CVPR'21. According to some product reasons, we are not planning to release the training/testing codes and models. However, we will release the dataset and the scripts to prepare the dataset.

TransFill-Reference-Inpainting This is the official repo for TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transf

80 Dec 8, 2022

Code release for NeurIPS 2020 paper "Co-Tuning for Transfer Learning"

Related tags

Overview

CoTuning

COCO 70 dataset

Dependencies

Datasets

Quick Start

Citation

Contact

You might also like...

Code release for the ICML 2021 paper "PixelTransformer: Sample Conditioned Signal Generation".

Code release for ICCV 2021 paper "Anticipative Video Transformer"

Official code release for ICCV 2021 paper SNARF: Differentiable Forward Skinning for Animating Non-rigid Neural Implicit Shapes.

This repo is the code release of EMNLP 2021 conference paper "Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories".

The code release of paper Low-Light Image Enhancement with Normalizing Flow

UDP++ (ECCVW 2020 Oral), (Winner of COCO 2020 Keypoint Challenge).

Code for paper ECCV 2020 paper: Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop.

git《Beta R-CNN: Looking into Pedestrian Detection from Another Perspective》(NeurIPS 2020) GitHub:[fig3]

Official implementation of "GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators" (NeurIPS 2020)

Comments

CoTuning execution result problem

How to determine the number of iter？

Reproducibility issue

Owner

THUML @ Tsinghua University

Code release for The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification (TIP 2020)

Code for ICE-BeeM paper - NeurIPS 2020

Code for Discriminative Sounding Objects Localization (NeurIPS 2020)

Code for the Population-Based Bandits Algorithm, presented at NeurIPS 2020.

This is the official code release for the paper Shape and Material Capture at Home

Code release for paper: The Boombox: Visual Reconstruction from Acoustic Vibrations

Code release to accompany paper "Geometry-Aware Gradient Algorithms for Neural Architecture Search."

Code release of paper "Deep Multi-View Stereo gone wild"

Code release for our paper, "SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo"