Code for the paper "M2m: Imbalanced Classification via Major-to-minor Translation" (CVPR 2020)

Last update: Oct 13, 2022

Related tags

Deep Learning M2m

Overview

M2m: Imbalanced Classification via Major-to-minor Translation

This repository contains code for the paper "M2m: Imbalanced Classification via Major-to-minor Translation" by Jaehyung Kim*, Jongheon Jeong* and Jinwoo Shin.

Dependencies

python3
pytorch >= 1.1.0
torchvision
tqdm

Scripts

Please check out run.sh for all the scripts to reproduce the CIFAR-10-LT results reported.

Training procedure of M2m

Train a baseline network g for generating minority samples

python train.py --no_over --ratio 100 --decay 2e-4 --model resnet32 --dataset cifar10 \
--lr 0.1 --batch-size 128 --name 'ERM' --warm 200 --epoch 200

Train another network f using M2m with the pre-trained g

python train.py -gen -r --ratio 100 --decay 2e-4 --model resnet32 --dataset cifar10 \
--lr 0.1 --batch-size 128 --name 'M2m' --beta 0.999 --lam 0.5 --gamma 0.9 \
--step_size 0.1 --attack_iter 10 --warm 160 --epoch 200 --net_g ./checkpoint/pre_trained_g.t7

We also provide a pre-trained ResNet-32 model of g at checkpoint/erm_r100_c10_trial1.t7, so one can directly use M2m without pre-training as follows:

python train.py -gen -r --ratio 100 --decay 2e-4 --model resnet32 --dataset cifar10 \
--lr 0.1 --batch-size 128 --name 'M2m' --beta 0.999 --lam 0.5 --gamma 0.9 \
--step_size 0.1 --attack_iter 10 --warm 160 --epoch 200 --net_g ./checkpoint/erm_r100_c10_trial1.t7

Comments

train M2m

great work! it seems to should add "--resume" when training M2m. (load ckpt_g) friendly warning. by the way, do you apply M2m on larger dataset, such as Imagenet?

opened by wangjl1993 4
Could you provide the processed CelebA-5 dataset?

Hi,

Thanks for your interesting work. I'd like to reproduce the experiments on CelebA-5, but it needs to be processed based on the official version as described in your paper. Could you please share a copy of the processed dataset or the script for processing?

Best Regards, Hongxin

opened by hongxin001 2
Loss function used to train baseline classifier g

Hello,

Great work guys,

I have a small question regarding the baseline classifier g.

Which loss are you using to train it? Is it Vanilla CE Loss? Because when analyzing accuracy per class on the unbalanced training data using the baseline classifier g with the weights that you provided, I found these already good accuracy values for unbalanced training: [99.8200, 99.8332, 99.2205, 97.8644, 98.6047, 97.1576, 97.8448, 99.2806, 97.5904, 96.0000].

Does it make sense to train it on more sophisticated losses like Weighted CE or so, to allow the model pick the features related to the minority samples better? Because on my dateset, the baseline classifier trained with CE performs really badly with a low accuracy near 5% on the minority sample of the training set. i.e. How well should the baseline classifier perform on the minority samples of the training data?

It would be great if you share the training procedure for reproducing the baseline classifier g (schedule, sampling methods, loss..).

I look forward to hearing from.

Many many thanks Best, Hssan

opened by hssandriss 1
How to reproduce the results on CIFAR10 and CIFAR100?
Hello All,

This is Sourav Das, currently working as a Project-Linked Person at Indian Statistical Institute, Kolkata.

I went through your CVPR 2020 paper, titled "M2m: Imbalanced Classification via Major-to-minor Translation" and would like to reproduce the result on CIFAR10 and CIFAR100 datasets.

I cloned the GitHub repo https://github.com/alinlab/M2m but I don't know

In which path to keep the CIFAR10 or CIFAR100 datasets?

In which format should the datasets be present?

Will it run with CIFAR10 and CIFAR100 datasets, directly downloaded from the site: https://www.cs.toronto.edu/~kriz/cifar.html or do I need to do some pre-processing to the datasets?

Awaiting an early response from you.

Thanks & Regards, Sourav Das
opened by SodaCoder 1
Guidence is needed to reproduce the results ? ?

i have recently learnt python and went through the some MOOCS of machine learning and deep learning. I have downloaded the whole code from this site. Any one kindly guide me how to run the code and reproduce the results ??

opened by sagheer-ahmed 1
Parameter for cifar10/100-r10/100

Hi, great work! I have trained cifar10_r10, cifar100_r10 and cifar100_r100. ALL the bACC of 3 ERM models is better but cifar100_r100 M2m model has SOTA performance. Can you tell me how to do to improve my model performance of c10_r10 and c100_r10?

opened by Huangszz 1

Owner

GitHub http://arxiv.org/abs/2004.00431

This repository contains the code for the CVPR 2020 paper "Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision"

697 Jan 6, 2023

Source code for CVPR 2020 paper "Learning to Forget for Meta-Learning"

L2F - Learning to Forget for Meta-Learning Sungyong Baik, Seokil Hong, Kyoung Mu Lee Source code for CVPR 2020 paper "Learning to Forget for Meta-Lear

29 May 22, 2022

[CVPR 2022] CoTTA Code for our CVPR 2022 paper Continual Test-Time Domain Adaptation

CoTTA Code for our CVPR 2022 paper Continual Test-Time Domain Adaptation Prerequisite Please create and activate the following conda envrionment. To r

87 Jan 8, 2023

PyTorch implementation of CVPR 2020 paper (Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence) and pre-trained model on ImageNet dataset

Reference-Based-Sketch-Image-Colorization-ImageNet This is a PyTorch implementation of CVPR 2020 paper (Reference-Based Sketch Image Colorization usin

11 Jul 28, 2022

Code accompanying "Dynamic Neural Relational Inference" from CVPR 2020

Code accompanying "Dynamic Neural Relational Inference" This codebase accompanies the paper "Dynamic Neural Relational Inference" from CVPR 2020. This

48 Dec 23, 2022

Official code for "End-to-End Optimization of Scene Layout" -- including VAE, Diff Render, SPADE for colorization (CVPR 2020 Oral)

End-to-End Optimization of Scene Layout Code release for: End-to-End Optimization of Scene Layout CVPR 2020 (Oral) Project site, Bibtex For help conta

41 Dec 9, 2022

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

Code for the paper "M2m: Imbalanced Classification via Major-to-minor Translation" (CVPR 2020)

Related tags

Overview

M2m: Imbalanced Classification via Major-to-minor Translation

Dependencies

Scripts

Training procedure of M2m

Comments

train M2m

Could you provide the processed CelebA-5 dataset?

Loss function used to train baseline classifier g

How to reproduce the results on CIFAR10 and CIFAR100?

Guidence is needed to reproduce the results ? ?

Parameter for cifar10/100-r10/100

Owner

This repository contains the code for the CVPR 2020 paper "Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision"

Source code for CVPR 2020 paper "Learning to Forget for Meta-Learning"

[CVPR 2022] CoTTA Code for our CVPR 2022 paper Continual Test-Time Domain Adaptation

PyTorch implementation of CVPR 2020 paper (Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence) and pre-trained model on ImageNet dataset

Code accompanying "Dynamic Neural Relational Inference" from CVPR 2020

Official code for "End-to-End Optimization of Scene Layout" -- including VAE, Diff Render, SPADE for colorization (CVPR 2020 Oral)

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.

TensorFlow code for the neural network presented in the paper: "Structural Language Models of Code" (ICML'2020)

Learning to Simulate Dynamic Environments with GameGAN (CVPR 2020)

An official implementation of "SFNet: Learning Object-aware Semantic Correspondence" (CVPR 2019, TPAMI 2020) in PyTorch.

Unofficial implementation of "TTNet: Real-time temporal and spatial video analysis of table tennis" (CVPR 2020)

git《Investigating Loss Functions for Extreme Super-Resolution》(CVPR 2020) GitHub:

Block-wisely Supervised Neural Architecture Search with Knowledge Distillation (CVPR 2020)

《Train in Germany, Test in The USA: Making 3D Object Detectors Generalize》(CVPR 2020)

《Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching》(CVPR 2020)

From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (CVPR'2020)

Pixel Consensus Voting for Panoptic Segmentation (CVPR 2020)

The official implementation of Equalization Loss v1 & v2 (CVPR 2020, 2021) based on MMDetection.