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

(Personalized) Page-Rank computation using PyTorch

Differentiable Quantum Chemistry (only Differentiable Density Functional Theory and Hartree Fock at the moment)

[CVPR 2021] NormalFusion: Real-Time Acquisition of Surface Normals for High-Resolution RGB-D Scanning

A New Open-Source Off-road Environment for Benchmark Generalization of Autonomous Driving

[ICCV 2021] Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation

Curved Projection Reformation

Library for fast text representation and classification.

Pytorch implementation of the paper "Optimization as a Model for Few-Shot Learning"

a reimplementation of UnFlow in PyTorch that matches the official TensorFlow version

Code for "Multi-Time Attention Networks for Irregularly Sampled Time Series", ICLR 2021.

Torch-ngp - A pytorch implementation of the hash encoder proposed in instant-ngp

git《FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding》(CVPR 2021) GitHub: [fig8]

Lepard: Learning Partial point cloud matching in Rigid and Deformable scenes

This repository contains source code for the Situated Interactive Language Grounding (SILG) benchmark

Code for our paper: Online Variational Filtering and Parameter Learning

VolumeGAN - 3D-aware Image Synthesis via Learning Structural and Textural Representations

Minimal fastai code needed for working with pytorch

This is the code of "Multi-view Contrastive Graph Clustering" in NeurlPS 2021.

High-resolution networks and Segmentation Transformer for Semantic Segmentation

The official implementation of paper "Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks" (IJCV under review).