Pytorch implementation of the AAAI 2022 paper "Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification"

Overview

[AAAI22] Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification

We point out the overlooked unbiasedness in long-tailed classification: models should perform well on both imbalanced and balanced test distributions. To tackle this challenge, we propose a novel training paradigm called Cross-Domain Empirical Risk Minimization (xERM). xERM consists of two ERM terms, which are the cross-entropy losses with different supervisions: one is the ground-truth label from the seen imbalanced domain, and the other is the prediction of a balanced model. The imbalanced domain empirical risk encourages the model to learn from the ground-truth annotations from the imbalanced distribution, which favors the head classes. The balanced domain empirical risk encourages the model to learn from the prediction of a balanced model, which imagines a balanced distribution and prefers the tail classes. These two risks are weighted to take advantage of both, i.e., protect the model training from being neither too “head biased” nor too “tail biased”, and can achieve the unbiasedness.

The codes are organized into three folders:

  1. xERM.PC.public uses Post-Compensated Softmax (PC) as balanced model to implement xERM.
  2. xERM.TDE.public uses Total Direct Effect (TDE) as balanced model to implement xERM.
  3. xERM.RIDE.public uses RIDE as balanced model to implement xERM.

Citation

If you find our paper or this project helps your research, please kindly consider citing our paper in your publication.

@inproceedings{beierxERM,
  title={Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification},
  author={Zhu, Beier and Niu, Yulei and Hua, Xian-Sheng and Zhang, Hanwang},
  booktitle={AAAI Conference on Artificial Intelligence},
  year={2022}
}

Update Logs

  • 28 Dec 2021, Release train and eval code of xERM-PC on CIFAR100-LT and ImageNet-LT Dataset.
You might also like...
Official implementation for paper Knowledge Bridging for Empathetic Dialogue Generation (AAAI 2021).
Official implementation for paper Knowledge Bridging for Empathetic Dialogue Generation (AAAI 2021).

Knowledge Bridging for Empathetic Dialogue Generation This is the official implementation for paper Knowledge Bridging for Empathetic Dialogue Generat

PyTorch Implementation for AAAI'21
PyTorch Implementation for AAAI'21 "Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response Selection"

UMS for Multi-turn Response Selection Implements the model described in the following paper Do Response Selection Models Really Know What's Next? Utte

Official PyTorch implementation of
Official PyTorch implementation of "Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning" (AAAI 2021)

Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning Official PyTorch implementation of "Proxy Synthesis: Learning with Synthetic

Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding (AAAI 2020) - PyTorch Implementation

Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding PyTorch implementation for the Scalable Attentive Sentence-Pair Modeling vi

[CVPR 2022] CoTTA Code for our CVPR 2022 paper Continual Test-Time Domain Adaptation

CoTTA Code for our CVPR 2022 paper Continual Test-Time Domain Adaptation Prerequisite Please create and activate the following conda envrionment. To r

This is the code for the paper
This is the code for the paper "Contrastive Clustering" (AAAI 2021)

Contrastive Clustering (CC) This is the code for the paper "Contrastive Clustering" (AAAI 2021) Dependency python=3.7 pytorch=1.6.0 torchvision=0.8

Source code for paper "Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling", AAAI 2021

ATLOP Code for AAAI 2021 paper Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling. If you make use of this co

This is the repository for the AAAI 21 paper [Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning].

CG3 This is the repository for the AAAI 21 paper [Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning]. R

Official implementation for (Show, Attend and Distill: Knowledge Distillation via Attention-based Feature Matching, AAAI-2021)

Show, Attend and Distill: Knowledge Distillation via Attention-based Feature Matching Official pytorch implementation of "Show, Attend and Distill: Kn

Comments
  • xERM-PC performance

    xERM-PC performance

    Dear Beier, I got a problem that I could not get your accuracy of 53.2 with xERM-PC code. My accuracy result is 0.527 with your config ce.yaml. The accuracies are : - Imbalanced Acc 0.461 Balanced Acc 0.513 xERM Acc 0.527 Could you give some hints about how to reproduce your result?

    Best

    opened by zuglerQ 1
  • xERM-TDE ImageNet Performance

    xERM-TDE ImageNet Performance

    Dear Beier, Thank you for your innovative work and I am really interested in it. However, when training the ImageNet_LT dataset with xERM-TDE method, I got low performance only 14.4 in the overall accuracy. I would like to ask, is it convenient to share the ImageNet_LT training code or configs there to make sure we could get your sota results?

    opened by zuglerQ 2
Owner
PatatiPatata
PatatiPatata
Code for the AAAI-2022 paper: Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification

Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification (AAAI 2022) Prerequisite PyTorch >= 1.2.0 P

null 16 Sep 27, 2022
An official source code for paper Deep Graph Clustering via Dual Correlation Reduction, accepted by AAAI 2022

Dual Correlation Reduction Network An official source code for paper Deep Graph Clustering via Dual Correlation Reduction, accepted by AAAI 2022. Any

yueliu1999 75 Nov 16, 2022
Official repository of the AAAI'2022 paper "Contrast and Generation Make BART a Good Dialogue Emotion Recognizer"

CoG-BART Contrast and Generation Make BART a Good Dialogue Emotion Recognizer Quick Start: To run the model on test sets of four datasets, Download th

null 36 Nov 9, 2022
Imposter-detector-2022 - HackED 2022 Team 3IQ - 2022 Imposter Detector

HackED 2022 Team 3IQ - 2022 Imposter Detector By Aneeljyot Alagh, Curtis Kan, Jo

Joshua Ji 3 Aug 20, 2022
ShuttleNet: Position-aware Fusion of Rally Progress and Player Styles for Stroke Forecasting in Badminton (AAAI 2022)

ShuttleNet: Position-aware Rally Progress and Player Styles Fusion for Stroke Forecasting in Badminton (AAAI 2022) Official code of the paper ShuttleN

Wei-Yao Wang 10 Nov 4, 2022
Attention-based Transformation from Latent Features to Point Clouds (AAAI 2022)

Attention-based Transformation from Latent Features to Point Clouds This repository contains a PyTorch implementation of the paper: Attention-based Tr

null 12 Nov 11, 2022
Code for One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning (AAAI 2022)

One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning (AAAI 2022) Paper | Demo Requirements Python >= 3.6 , Pytorch >

FuxiVirtualHuman 72 Nov 15, 2022
Parallel and High-Fidelity Text-to-Lip Generation; AAAI 2022 ; Official code

Parallel and High-Fidelity Text-to-Lip Generation This repository is the official PyTorch implementation of our AAAI-2022 paper, in which we propose P

Zhying 75 Nov 15, 2022
Official implementation of AAAI-21 paper "Label Confusion Learning to Enhance Text Classification Models"

Description: This is the official implementation of our AAAI-21 accepted paper Label Confusion Learning to Enhance Text Classification Models. The str

null 97 Nov 9, 2022
Implementation of accepted AAAI 2021 paper: Deep Unsupervised Image Hashing by Maximizing Bit Entropy

Deep Unsupervised Image Hashing by Maximizing Bit Entropy This is the PyTorch implementation of accepted AAAI 2021 paper: Deep Unsupervised Image Hash

null 59 Oct 12, 2022