Official Pytorch implementation of "Learning Debiased Representation via Disentangled Feature Augmentation (Neurips 2021, Oral)"

Last update: Dec 17, 2022

Overview

Learning Debiased Representation via Disentangled Feature Augmentation (Neurips 2021, Oral): Official Project Webpage

This repository provides the official PyTorch implementation of the following paper:

Learning Debiased Representation via Disentangled Feature Augmentation
Jungsoo Lee* (KAIST AI, Kakao Enterprise), Eungyeup Kim* (KAIST AI, Kakao Enterprise),
Juyoung Lee (Kakao Enterprise), Jihyeon Lee (KAIST AI), and Jaegul Choo (KAIST AI)
(* indicates equal contribution. The order of first authors was chosen by tossing a coin.)
NeurIPS 2021, Oral

Paper: Arxiv

Abstract: Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability when evaluated on unbiased datasets. Existing approaches for debiasing often identify and emphasize those samples with no such correlation (i.e., bias-conflicting) without defining the bias type in advance. However, such bias-conflicting samples are significantly scarce in biased datasets, limiting the debiasing capability of these approaches. This paper first presents an empirical analysis revealing that training with "diverse" bias-conflicting samples beyond a given training set is crucial for debiasing as well as the generalization capability. Based on this observation, we propose a novel feature-level data augmentation technique in order to synthesize diverse bias-conflicting samples. To this end, our method learns the disentangled representation of (1) the intrinsic attributes (i.e., those inherently defining a certain class) and (2) bias attributes (i.e., peripheral attributes causing the bias), from a large number of bias-aligned samples, the bias attributes of which have strong correlation with the target variable. Using the disentangled representation, we synthesize bias-conflicting samples that contain the diverse intrinsic attributes of bias-aligned samples by swapping their latent features. By utilizing these diversified bias-conflicting features during the training, our approach achieves superior classification accuracy and debiasing results against the existing baselines on both synthetic as well as a real-world dataset.

Code Contributors

Jungsoo Lee [Website] [LinkedIn] [Google Scholar] (KAIST AI, Kakao Enterprise)
Eungyeup Kim [Website] [LinkedIn] [Google Scholar] (KAIST AI, Kakao Enterprise)
Juyoung Lee [Website] (Kakao Enterprise)

Pytorch Implementation

Installation

Clone this repository.

git clone https://github.com/kakaoenterprise/Learning-Debiased-Disentangled.git
cd Learning-Debiased-Disentangled
pip install -r requirements.txt

Datasets

We used three datasets in our paper.

Download the datasets with the following url. Note that BFFHQ is the dataset used in "BiaSwap: Removing Dataset Bias with Bias-Tailored Swapping Augmentation" (Kim et al., ICCV 2021). Unzip the files and the directory structures will be as following:

cmnist
 └ 0.5pct / 1pct / 2pct / 5pct
     └ align
     └ conlict
     └ valid
 └ test

cifar10c
 └ 0.5pct / 1pct / 2pct / 5pct
     └ align
     └ conlict
     └ valid
 └ test

bffhq
 └ 0.5pct
 └ valid
 └ test

How to Run

CMNIST

Vanilla

python train.py --dataset cmnist --exp=cmnist_0.5_vanilla --lr=0.01 --percent=0.5pct --train_vanilla --tensorboard --wandb
python train.py --dataset cmnist --exp=cmnist_1_vanilla --lr=0.01 --percent=1pct --train_vanilla --tensorboard --wandb
python train.py --dataset cmnist --exp=cmnist_2_vanilla --lr=0.01 --percent=2pct --train_vanilla --tensorboard --wandb
python train.py --dataset cmnist --exp=cmnist_5_vanilla --lr=0.01 --percent=5pct --train_vanilla --tensorboard --wandb

bash scripts/run_cmnist_vanilla.sh

Ours

python train.py --dataset cmnist --exp=cmnist_0.5_ours --lr=0.01 --percent=0.5pct --curr_step=10000 --lambda_swap=1 --lambda_dis_align=10 --lambda_swap_align=10 --use_lr_decay --lr_decay_step=10000 --lr_gamma=0.5 --train_ours --tensorboard --wandb
python train.py --dataset cmnist --exp=cmnist_1_ours --lr=0.01 --percent=1pct  --curr_step=10000 --lambda_swap=1 --lambda_dis_align=10 --lambda_swap_align=10 --use_lr_decay --lr_decay_step=10000 --lr_gamma=0.5 --train_ours --tensorboard --wandb
python train.py --dataset cmnist --exp=cmnist_2_ours --lr=0.01 --percent=2pct  --curr_step=10000 --lambda_swap=1 --lambda_dis_align=10 --lambda_swap_align=10 --use_lr_decay --lr_decay_step=10000 --lr_gamma=0.5 --train_ours --tensorboard --wandb
python train.py --dataset cmnist --exp=cmnist_5_ours --lr=0.01 --percent=5pct  --curr_step=10000 --lambda_swap=1 --lambda_dis_align=10 --lambda_swap_align=10 --use_lr_decay --lr_decay_step=10000 --lr_gamma=0.5 --train_ours --tensorboard --wandb

bash scripts/run_cmnist_ours.sh

Corrupted CIFAR10

Vanilla

python train.py --dataset cifar10c --exp=cifar10c_0.5_vanilla --lr=0.001 --percent=0.5pct --train_vanilla --tensorboard --wandb
python train.py --dataset cifar10c --exp=cifar10c_1_vanilla --lr=0.001 --percent=1pct --train_vanilla --tensorboard --wandb
python train.py --dataset cifar10c --exp=cifar10c_2_vanilla --lr=0.001 --percent=2pct --train_vanilla --tensorboard --wandb
python train.py --dataset cifar10c --exp=cifar10c_5_vanilla --lr=0.001 --percent=5pct --train_vanilla --tensorboard --wandb

bash scripts/run_cifar10c_vanilla.sh

Ours

python train.py --dataset cifar10c --exp=cifar10c_0.5_ours --lr=0.0005 --percent=0.5pct --curr_step=10000 --lambda_swap=1 --lambda_dis_align=1 --lambda_swap_align=1 --use_lr_decay --lr_decay_step=10000 --lr_gamma=0.5 --train_ours --tensorboard --wandb
python train.py --dataset cifar10c --exp=cifar10c_1_ours --lr=0.001 --percent=1pct --curr_step=10000 --lambda_swap=1 --lambda_dis_align=5 --lambda_swap_align=5 --use_lr_decay --lr_decay_step=10000 --lr_gamma=0.5 --train_ours --tensorboard --wandb
python train.py --dataset cifar10c --exp=cifar10c_2_ours --lr=0.001 --percent=2pct --curr_step=10000 --lambda_swap=1 --lambda_dis_align=5 --lambda_swap_align=5 --use_lr_decay --lr_decay_step=10000 --lr_gamma=0.5 --train_ours --tensorboard --wandb
python train.py --dataset cifar10c --exp=cifar10c_5_ours --lr=0.001 --percent=5pct --curr_step=10000 --lambda_swap=1 --lambda_dis_align=1 --lambda_swap_align=1 --use_lr_decay --lr_decay_step=10000 --lr_gamma=0.5 --train_ours --tensorboard --wandb

bash scripts/run_cifar10c_ours.sh

BFFHQ

Vanilla

python train.py --dataset bffhq --exp=bffhq_0.5_vanilla --lr=0.0001 --percent=0.5pct --train_vanilla --tensorboard --wandb

bash scripts/run_bffhq_vanilla.sh

Ours

python train.py --dataset bffhq --exp=bffhq_0.5_ours --lr=0.0001 --percent=0.5pct --lambda_swap=0.1 --curr_step=10000 --use_lr_decay --lr_decay_step=10000 --lambda_dis_align 2. --lambda_swap_align 2. --dataset bffhq --train_ours --tensorboard --wandb

bash scripts/run_bffhq_ours.sh

Pretrained Models

In order to test our pretrained models, run the following command.

python test.py --pretrained_path=
   
     --dataset=
    
      --percent=

We provide the pretrained models in the following urls.
CMNIST 0.5pct
CMNIST 1pct
CMNIST 2pct
CMNIST 5pct

CIFAR10C 0.5pct
CIFAR10C 1pct
CIFAR10C 2pct
CIFAR10C 5pct

BFFHQ 0.5pct

Citations

Bibtex coming soon!

Contact

Jungsoo Lee

Eungyeup Kim

Juyoung Lee

Kakao Enterprise/Vision Team

Acknowledgments

This work was mainly done when both of the first authors were doing internship at Vision Team/AI Lab/Kakao Enterprise. Our pytorch implementation is based on LfF. Thanks for the implementation.

Official Pytorch implementation of "Learning Debiased Representation via Disentangled Feature Augmentation (Neurips 2021, Oral)"

Related tags

Overview

Learning Debiased Representation via Disentangled Feature Augmentation (Neurips 2021, Oral): Official Project Webpage

Code Contributors

Pytorch Implementation

Installation

Datasets

How to Run

CMNIST

Vanilla

Ours

Corrupted CIFAR10

Vanilla

Ours

BFFHQ

Vanilla

Ours

Pretrained Models

Citations

Contact

Acknowledgments

Owner

Kakao Enterprise Corp.

The official implementation of paper Siamese Transformer Pyramid Networks for Real-Time UAV Tracking, accepted by WACV22

Code for our method RePRI for Few-Shot Segmentation. Paper at http://arxiv.org/abs/2012.06166

EMNLP 2021 Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections

A demonstration of using a live Tensorflow session to create an interactive face-GAN explorer.

Mixed Neural Likelihood Estimation for models of decision-making

Data cleaning, missing value handle, EDA use in this project

Official PyTorch implementation of our AAAI22 paper: TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework via Self-Supervised Multi-Task Learning. Code will be available soon.

MoCoGAN: Decomposing Motion and Content for Video Generation

Awesome-google-colab - Google Colaboratory Notebooks and Repositories

Official pytorch implementation for Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion (CVPR 2022)

🥇 LG-AI-Challenge 2022 1위 솔루션 입니다.

This project aims at providing a concise, easy-to-use, modifiable reference implementation for semantic segmentation models using PyTorch.

ReConsider is a re-ranking model that re-ranks the top-K (passage, answer-span) predictions of an Open-Domain QA Model like DPR (Karpukhin et al., 2020).

A Tensorflow implementation of the Text Conditioned Auxiliary Classifier Generative Adversarial Network for Generating Images from text descriptions

A PyTorch implementation of "Pathfinder Discovery Networks for Neural Message Passing"

Free-duolingo-plus - Duolingo account creator that uses your invite code to get you free duolingo plus

From the basics to slightly more interesting applications of Tensorflow

Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging, ICCV2021 [PyTorch Code]

The official implementation code of "PlantStereo: A Stereo Matching Benchmark for Plant Surface Dense Reconstruction."

PyTorch implementation of the paper Ultra Fast Structure-aware Deep Lane Detection