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

Last update: Oct 13, 2022

Related tags

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

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

Owner

In this project, two programs can help you take full agvantage of time on the model training with a remote server

Deep Learning GPU Training System

Simple image captioning model - CLIP prefix captioning.

[CVPR 2022 Oral] TubeDETR: Spatio-Temporal Video Grounding with Transformers

The final project of "Applying AI to EHR Data" of "AI for Healthcare" nanodegree - Udacity.

Accelerated deep learning R&D

Official implementation for "Style Transformer for Image Inversion and Editing" (CVPR 2022)

Keras Image Embeddings using Contrastive Loss

Object classification with basic computer vision techniques

Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks

Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning

PyTorch implementation of "MLP-Mixer: An all-MLP Architecture for Vision" Tolstikhin et al. (2021)

Python TFLite scripts for detecting objects of any class in an image without knowing their label.

pytorch implementation for PointNet

Few-shot NLP benchmark for unified, rigorous eval

Deep Learning Training Scripts With Python

Official implementation of VQ-Diffusion

A toolkit for Lagrangian-based constrained optimization in Pytorch

Graph Convolutional Networks for Temporal Action Localization (ICCV2019)

optimization routines for hyperparameter tuning