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

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.

Create images and texts with the First Order Generative Adversarial Networks

Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...

Using CNN to mimic the driver based on training data from Torcs

Weighing Counts: Sequential Crowd Counting by Reinforcement Learning

Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding (CVPR2022)

QA-GNN: Question Answering using Language Models and Knowledge Graphs

Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning, NeurIPS 2021 (Spotlight)

Library for 8-bit optimizers and quantization routines.

An implementation of chunked, compressed, N-dimensional arrays for Python.

Sharpness-Aware Minimization for Efficiently Improving Generalization

Enabling dynamic analysis of Legacy Embedded Systems in full emulated environment

Code and datasets for the paper "KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction"

Learning View Priors for Single-view 3D Reconstruction (CVPR 2019)

App customer segmentation cohort rfm clustering

An Unpaired Sketch-to-Photo Translation Model

Pre-Training 3D Point Cloud Transformers with Masked Point Modeling

SAMO: Streaming Architecture Mapping Optimisation

Backend code to use MCPI's python API to make infinite worlds with custom generation

Reinforcement learning for self-driving in a 3D simulation

code for "Self-supervised edge features for improved Graph Neural Network training",