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

Neural Style and MSG-Net

Rendering color and depth images for ShapeNet models.

EMNLP 2021 paper Models and Datasets for Cross-Lingual Summarisation.

Kalidokit is a blendshape and kinematics solver for Mediapipe/Tensorflow.js face, eyes, pose, and hand tracking models

My personal Home Assistant configuration.

Fast convergence of detr with spatially modulated co-attention

Automatic voice-synthetised summaries of latest research papers on arXiv

PyTorch Implementation of PIXOR: Real-time 3D Object Detection from Point Clouds

A-ESRGAN aims to provide better super-resolution images by using multi-scale attention U-net discriminators.

This repository contains all data used for writing a research paper Multiple Object Trackers in OpenCV: A Benchmark, presented in ISIE 2021 conference in Kyoto, Japan.

The official implementation for ACL 2021 "Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval".

Dirty Pixels: Towards End-to-End Image Processing and Perception

Code Repo for the ACL21 paper "Common Sense Beyond English: Evaluating and Improving Multilingual LMs for Commonsense Reasoning"

PyTorch implementation of ARM-Net: Adaptive Relation Modeling Network for Structured Data.

Code for the paper "Relation of the Relations: A New Formalization of the Relation Extraction Problem"

Codebase for ECCV18 "The Sound of Pixels"

Model-based reinforcement learning in TensorFlow

Prometheus exporter for Cisco Unified Computing System (UCS) Manager

Image super-resolution through deep learning

Logistic Bandit experiments. Official code for the paper "Jointly Efficient and Optimal Algorithms for Logistic Bandits".