Official implementation of Influence-balanced Loss for Imbalanced Visual Classification in PyTorch.

Related tags

Deep Learning IB-Loss
Overview

Influence-balanced Loss for Imbalanced Visual Classification (ICCV, 2021)

This is the official implementation of Influence-balanced Loss for Imbalanced Visual Classification in PyTorch. The code heavily relies on LDAM-DRW.

Requirements

All codes are written by Python 3.7, and 'requirements.txt' contains required Python packages. To install requirements:

pip install -r requirements.txt

Dataset

Create 'data/' directory and download original data in the directory to make imbalanced versions.

  • Imbalanced CIFAR. The original data will be downloaded and converted by imbalancec_cifar.py.
  • Imbalanced Tiny ImageNet. Download the data first, and convert them by imbalance_tinyimagenet.py.
  • The paper also reports results on iNaturalist 2018. We will update the code for iNaturalist 2018 later.

Training

We provide several training examples:

CIFAR

  • CE baseline (CIFAR-100, long-tailed imabalance ratio of 100)
python cifar_train.py --dataset cifar100 --loss_type CE --train_rule None --imb_type exp --imb_factor 0.01 --epochs 200 --num_classes 100 --gpu 0
  • IB (CIFAR-100, long-tailed imabalance ratio of 100)
python cifar_train.py --dataset cifar100 --loss_type IB --train_rule IBReweight --imb_type exp --imb_factor 0.01 --epochs 200 --num_classes 100 --start_ib_epoch 100 --gpu 0
  • IB + CB (CIFAR-100, long-tailed imabalance ratio of 100)
python cifar_train.py --dataset cifar100 --loss_type IB --train_rule CBReweight --imb_type exp --imb_factor 0.01 --epochs 200 --num_classes 100 --start_ib_epoch 100 --gpu 0
  • IB + Focal (CIFAR-100, long-tailed imabalance ratio of 100)
python cifar_train.py --dataset cifar100 --loss_type IBFocal --train_rule IBReweight --imb_type exp --imb_factor 0.01 --epochs 200 --num_classes 100 --start_ib_epoch 100 --gpu 0

Tiny ImageNet

  • CE baseline (long-tailed imabalance ratio of 100)
python tinyimage_train.py --dataset tinyimagenet -a resnet18 --loss_type CE --train_rule None --imb_type exp --imb_factor 0.01 --epochs 100 --lr 0.1  --num_classes 200
  • IB (long-tailed imabalance ratio of 100)
python tinyimage_train.py --dataset tinyimagenet -a resnet18 --loss_type IB --train_rule IBReweight --imb_type exp --imb_factor 0.01 --epochs 100 --lr 0.1  --num_classes 200 --start_ib_epoch 50

Citation

If you find our paper and repo useful, please cite our paper

You might also like...
Recall Loss for Semantic Segmentation (This repo implements the paper: Recall Loss for Semantic Segmentation)
Recall Loss for Semantic Segmentation (This repo implements the paper: Recall Loss for Semantic Segmentation)

Recall Loss for Semantic Segmentation (This repo implements the paper: Recall Loss for Semantic Segmentation) Download Synthia dataset The model uses

null 32 Sep 21, 2022
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.

Imbalanced Dataset Sampler Introduction In many machine learning applications, we often come across datasets where some types of data may be seen more

Ming 2k Jan 8, 2023
Official implementation of our paper
Official implementation of our paper "LLA: Loss-aware Label Assignment for Dense Pedestrian Detection" in Pytorch.

LLA: Loss-aware Label Assignment for Dense Pedestrian Detection This project provides an implementation for "LLA: Loss-aware Label Assignment for Dens

null 35 Dec 6, 2022
Official PyTorch Implementation of Rank & Sort Loss [ICCV2021]
Official PyTorch Implementation of Rank & Sort Loss [ICCV2021]

Rank & Sort Loss for Object Detection and Instance Segmentation The official implementation of Rank & Sort Loss. Our implementation is based on mmdete

Kemal Oksuz 229 Dec 20, 2022
Official pytorch implementation of "Feature Stylization and Domain-aware Contrastive Loss for Domain Generalization" ACMMM 2021 (Oral)

Feature Stylization and Domain-aware Contrastive Loss for Domain Generalization This is an official implementation of "Feature Stylization and Domain-

null 22 Sep 22, 2022
Location-Sensitive Visual Recognition with Cross-IOU Loss
Location-Sensitive Visual Recognition with Cross-IOU Loss

The trained models are temporarily unavailable, but you can train the code using reasonable computational resource. Location-Sensitive Visual Recognit

Kaiwen Duan 146 Dec 25, 2022
Code release for The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification (TIP 2020)
Code release for The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification (TIP 2020)

The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification Code release for The Devil is in the Channels: Mutual-Channel

PRIS-CV: Computer Vision Group 230 Dec 31, 2022
[ICML 2021, Long Talk] Delving into Deep Imbalanced Regression
[ICML 2021, Long Talk] Delving into Deep Imbalanced Regression

Delving into Deep Imbalanced Regression This repository contains the implementation code for paper: Delving into Deep Imbalanced Regression Yuzhe Yang

Yuzhe Yang 568 Dec 30, 2022
MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data

This repository is the official PyTorch implementation of Meta-Balance. Find the paper on arxiv MetaBalance: High-Performance Neural Networks for Clas

Arpit Bansal 20 Oct 18, 2021
Comments
  • IB+CB Loss

    IB+CB Loss

    Thank you very much for your excellent work. Excuse me, is the combination of IB loss and CB loss multiplied by IB weighting factor on the basis of CB loss。that is I want to know the mathematical expression of CB + IB loss. I look forward to your reply！

    opened by Never-Walk-Away 2
  • Is there any criterion for choosing alpha?

    Is there any criterion for choosing alpha?

    I wish to adopt IB loss to YOLOX for object detection.... However after several epoch finetuing the mAP drop from 80% to 30%.
    I choose 1000 for alpha. When calculating the grad, I use the channel values of every pixel point on the input feature map of the classfier pred as "feature vector".

    opened by LyuYuxin 2
  • NaN or Inf found in input tensor.

    NaN or Inf found in input tensor.

    Hello,I am very interested in your paper, thank you for your work, but I have some problems.may I ask why such a prompt appears,thank you

    C:\Users\Big sheng\Desktop\program\IB-Loss-main\tinyimage_train.py:335: RuntimeWarning: invalid value encountered in true_divide cls_acc = cls_hit / cls_cnt NaN or Inf found in input tensor. NaN or Inf found in input tensor. NaN or Inf found in input tensor. NaN or Inf found in input tensor. NaN or Inf found in input tensor. NaN or Inf found in input tensor. NaN or Inf found in input tensor. NaN or Inf found in input tensor. NaN or Inf found in input tensor. NaN or Inf found in input tensor.

    opened by 125555544896322 0
Owner
Seulki Park
PhD Student in Electrical and Computer Engineering at Seoul National University, Korea
Seulki Park
GitHub
Official Pytorch implementation of "Unbiased Classification Through Bias-Contrastive and Bias-Balanced Learning (NeurIPS 2021)

Unbiased Classification Through Bias-Contrastive and Bias-Balanced Learning (NeurIPS 2021) Official Pytorch implementation of Unbiased Classification

Youngkyu 17 Jan 1, 2023
imbalanced-DL: Deep Imbalanced Learning in Python

imbalanced-DL: Deep Imbalanced Learning in Python Overview imbalanced-DL (imported as imbalanceddl) is a Python package designed to make deep imbalanc

NTUCSIE CLLab 19 Dec 28, 2022
The repo contains the code of the ACL2020 paper `Dice Loss for Data-imbalanced NLP Tasks`

Dice Loss for NLP Tasks This repository contains code for Dice Loss for Data-imbalanced NLP Tasks at ACL2020. Setup Install Package Dependencies The c

null 223 Dec 17, 2022
A pytorch-version implementation codes of paper: "BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation"

BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation A pytorch-version implementation

null 11 Oct 8, 2022
Implement of "Training deep neural networks via direct loss minimization" in PyTorch for 0-1 loss

This is the implementation of "Training deep neural networks via direct loss minimization" published at ICML 2016 in PyTorch. The implementation targe

Cuong Nguyen 1 Jan 18, 2022
An implementation for the loss function proposed in Decoupled Contrastive Loss paper.

Decoupled-Contrastive-Learning This repository is an implementation for the loss function proposed in Decoupled Contrastive Loss paper. Requirements P

Ramin Nakhli 71 Dec 4, 2022
Official implementation for the paper: "Multi-label Classification with Partial Annotations using Class-aware Selective Loss"

Multi-label Classification with Partial Annotations using Class-aware Selective Loss Paper | Pretrained models Official PyTorch Implementation Emanuel

null 99 Dec 27, 2022
Source code of "Hold me tight! Influence of discriminative features on deep network boundaries"

Hold me tight! Influence of discriminative features on deep network boundaries This is the source code to reproduce the experiments of the NeurIPS 202

EPFL LTS4 19 Dec 10, 2021
constructing maps of intellectual influence from publication data

Influencemap Project @ ANU Influence in the academic communities has been an area of interest for researchers. This can be seen in the popularity of a

CS Metrics 13 Jun 18, 2022
A Pytorch implementation of CVPR 2021 paper "RSG: A Simple but Effective Module for Learning Imbalanced Datasets"

RSG: A Simple but Effective Module for Learning Imbalanced Datasets (CVPR 2021) A Pytorch implementation of our CVPR 2021 paper "RSG: A Simple but Eff

null 120 Dec 12, 2022