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

李云龙二次元风格化!打滚卖萌，使用了animeGANv2进行了视频的风格迁移

AntroPy: entropy and complexity of (EEG) time-series in Python

Repository for the semantic WMI loss

Constrained Language Models Yield Few-Shot Semantic Parsers

WiFi-based Multi-task Sensing

[ICCV'21] Pri3D: Can 3D Priors Help 2D Representation Learning?

TalkingHead-1KH is a talking-head dataset consisting of YouTube videos

Implementation of the ivis algorithm as described in the paper Structure-preserving visualisation of high dimensional single-cell datasets.

BookMyShowPC - Movie Ticket Reservation App made with Tkinter

A framework for Quantification written in Python

This repository contains codes of ICCV2021 paper: SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation

Utility code for use with PyXLL

Introducing neural networks to predict stock prices

Lorien: A Unified Infrastructure for Efficient Deep Learning Workloads Delivery

Official implementation of GraphMask as presented in our paper Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking.

MOpt-AFL provided by the paper "MOPT: Optimized Mutation Scheduling for Fuzzers"

Python project to take sound as input and output as RGB + Brightness values suitable for DMX

Learning Optical Flow from a Few Matches (CVPR 2021)

Live Hand Tracking Using Python

An open-access benchmark and toolbox for electricity price forecasting