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

Overview

Unbiased Classification Through Bias-Contrastive and Bias-Balanced Learning (NeurIPS 2021)

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

Setup

This setting requires CUDA 11. However, you can still use your own environment by installing requirements including PyTorch and Torchvision.

  1. Install conda environment and activate it
conda env create -f environment.yml
conda activate biascon
  1. Prepare dataset.
  • Biased MNIST
    By default, we set download=True for convenience.
    Thus, you only have to make the empty dataset directory with mkdir -p data/biased_mnist and run the code.

  • CelebA
    Download CelebA dataset under data/celeba

  • UTKFace
    Download UTKFace dataset under data/utk_face

  • ImageNet & ImageNet-A
    We use ILSVRC 2015 ImageNet dataset.
    Download ImageNet under ./data/imagenet and ImageNet-A under ./data/imagenet-a

Biased MNIST (w/ bias labels)

We use correlation {0.999, 0.997, 0.995, 0.99, 0.95, 0.9}.

Bias-contrastive loss (BiasCon)

python train_biased_mnist_bc.py --corr 0.999 --seed 1

Bias-balancing loss (BiasBal)

python train_biased_mnist_bb.py --corr 0.999 --seed 1

Joint use of BiasCon and BiasBal losses (BC+BB)

python train_biased_mnist_bc.py --bb 1 --corr 0.999 --seed 1

CelebA

We assess CelebA dataset with target attributes of HeavyMakeup (--task makeup) and Blonde (--task blonde).

Bias-contrastive loss (BiasCon)

python train_celeba_bc.py --task makeup --seed 1

Bias-balancing loss (BiasBal)

python train_celeba_bb.py --task makeup --seed 1

Joint use of BiasCon and BiasBal losses (BC+BB)

python train_celeba_bc.py --bb 1 --task makeup --seed 1

UTKFace

We assess UTKFace dataset biased toward Race (--task race) and Age (--task age) attributes.

Bias-contrastive loss (BiasCon)

python train_utk_face_bc.py --task race --seed 1

Bias-balancing loss (BiasBal)

python train_utk_face_bb.py --task race --seed 1

Joint use of BiasCon and BiasBal losses (BC+BB)

python train_utk_face_bc.py --bb 1 --task race --seed 1

Biased MNIST (w/o bias labels)

We use correlation {0.999, 0.997, 0.995, 0.99, 0.95, 0.9}.

Soft Bias-contrastive loss (SoftCon)

  1. Train a bias-capturing model and get bias features.
python get_biased_mnist_bias_features.py --corr 0.999 --seed 1
  1. Train a model with bias features.
python train_biased_mnist_softcon.py --corr 0.999 --seed 1

ImageNet

We use texture cluster information from ReBias (Bahng et al., 2020).

Soft Bias-contrastive loss (SoftCon)

  1. Train a bias-capturing model and get bias features.
python get_imagenet_bias_features.py --seed 1
  1. Train a model with bias features.
python train_imagenet_softcon.py --seed 1
Owner
Youngkyu
Machine Learning Engineer / Backend Engineer
Youngkyu
Metadata-Extractor - Metadata Extractor Script can be used to read in exif metadata

Metadata Extractor The exifextract script can be used to read in exif metadata f

1 Feb 16, 2022
Unsupervised Feature Ranking via Attribute Networks.

FRANe Unsupervised Feature Ranking via Attribute Networks (FRANe) converts a dataset into a network (graph) with nodes that correspond to the features

7 Sep 29, 2022
Oriented Response Networks, in CVPR 2017

Oriented Response Networks [Home] [Project] [Paper] [Supp] [Poster] Torch Implementation The torch branch contains: the official torch implementation

ZhouYanzhao 217 Dec 12, 2022
Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme (NeurIPS2021)

Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme (NeurIPS2021) Overview Prerequisites Linux Pytho

Shaojie Li 34 Mar 31, 2022
Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition

Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition How Fast Compare to Other Zero-Shot NAS Proxies on CIFAR-10/100 Pre-trained Model

190 Dec 29, 2022
Author's PyTorch implementation of TD3+BC, a simple variant of TD3 for offline RL

A Minimalist Approach to Offline Reinforcement Learning TD3+BC is a simple approach to offline RL where only two changes are made to TD3: (1) a weight

Scott Fujimoto 193 Dec 23, 2022
Fast (simple) spectral synthesis and emission-line fitting of DESI spectra.

FastSpecFit Introduction This repository contains code and documentation to perform fast, simple spectral synthesis and emission-line fitting of DESI

5 Aug 02, 2022
📚 Papermill is a tool for parameterizing, executing, and analyzing Jupyter Notebooks.

papermill is a tool for parameterizing, executing, and analyzing Jupyter Notebooks. Papermill lets you: parameterize notebooks execute notebooks This

nteract 5.1k Jan 03, 2023
Learning Versatile Neural Architectures by Propagating Network Codes

Learning Versatile Neural Architectures by Propagating Network Codes Mingyu Ding, Yuqi Huo, Haoyu Lu, Linjie Yang, Zhe Wang, Zhiwu Lu, Jingdong Wang,

Mingyu Ding 36 Dec 06, 2022
Author Disambiguation using Knowledge Graph Embeddings with Literals

Author Name Disambiguation with Knowledge Graph Embeddings using Literals This is the repository for the master thesis project on Knowledge Graph Embe

12 Oct 19, 2022
pytorch implementation of fast-neural-style

fast-neural-style 🌇 🚀 NOTICE: This codebase is no longer maintained, please use the codebase from pytorch examples repository available at pytorch/e

Abhishek Kadian 405 Dec 15, 2022
We are More than Our JOints: Predicting How 3D Bodies Move

We are More than Our JOints: Predicting How 3D Bodies Move Citation This repo contains the official implementation of our paper MOJO: @inproceedings{Z

72 Oct 20, 2022
Api's bulid in Flask perfom to manage Todo Task.

Citymall-task Api's bulid in Flask perfom to manage Todo Task. Installation Requrements : Python: 3.10.0 MongoDB create .env file with variables DB_UR

Aisha Tayyaba 1 Dec 17, 2021
Source code for EquiDock: Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking (ICLR 2022)

Source code for EquiDock: Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking (ICLR 2022) Please cite "Independent SE(3)-Equivar

Octavian Ganea 154 Jan 02, 2023
[CVPR 2022 Oral] Balanced MSE for Imbalanced Visual Regression https://arxiv.org/abs/2203.16427

Balanced MSE Code for the paper: Balanced MSE for Imbalanced Visual Regression Jiawei Ren, Mingyuan Zhang, Cunjun Yu, Ziwei Liu CVPR 2022 (Oral) News

Jiawei Ren 267 Jan 01, 2023
This repository contains the code for designing risk bounded motion plans for car-like robot using Carla Simulator.

Nonlinear Risk Bounded Robot Motion Planning This code simulates the bicycle dynamics of car by steering it on the road by avoiding another static car

8 Sep 03, 2022
Official repository for the ICCV 2021 paper: UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model.

UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model Official repository for the ICCV 2021 paper: UltraPose: Syn

MomoAILab 92 Dec 21, 2022
An efficient and easy-to-use deep learning model compression framework

TinyNeuralNetwork įŽ€äŊ“中文 TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework, which contains features like neura

Alibaba 441 Dec 25, 2022
Stacked Hourglass Network with a Multi-level Attention Mechanism: Where to Look for Intervertebral Disc Labeling

âš ī¸ ‎‎‎ A more recent and actively-maintained version of this code is available in ivadomed Stacked Hourglass Network with a Multi-level Attention Mech

Reza Azad 14 Oct 24, 2022
The authors' official PyTorch SigWGAN implementation

The authors' official PyTorch SigWGAN implementation This repository is the official implementation of [Sig-Wasserstein GANs for Time Series Generatio

9 Jun 16, 2022