Code release for General Greedy De-bias Learning

Last update: Mar 15, 2022

Related tags

Overview

General Greedy De-bias for Dataset Biases

This is an extention of "Greedy Gradient Ensemble for Robust Visual Question Answering" (ICCV 2021, Oral). The prerequisites can refer to GGE.

If you find this repo helpful, please cite

@article{han2021general,
	title={General Greedy De-bias Learning},
	author={Han, Xinzhe and Wang, Shuhui and Su, Chi and Huang, Qingming and Tian, Qi},
	journal={arXiv preprint arXiv:2112.10572 },
	year={2021}
}

@inproceedings{han2021greedy,
  title={Greedy gradient ensemble for robust visual question answering},
  author={Han, Xinzhe and Wang, Shuhui and Su, Chi and Huang, Qingming and Tian, Qi},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={1584--1593},
  year={2021}
}

GGD

The core of GGD is to decompose the CE loss of GGE. The pytorch implementation is

loss = -(logits.log_softmax(-1) * labels).mean() + weight * (logits.log_softmax(-1) * bias * labels).mean()

Biased-MNIST

Biased-MNIST is produced the same with Re-bias. Run the notebook in the MNIST folder. Modify data_label_correlation for different bias level.

VQA-CP

Codes for VQA-CP is updated in GGE. To train a model with new GGD-CR, set import base_model_sfce in mian.py and run

CUDA_VISIBLE_DEVICES=0 python main.py --dataset cpv2 --mode gge_iter --debias ce_decompose --topq 1 --topv -1 --qvp 5 --output []

Adversarial SQuAD

The experiment for AdQA is provided in squad folder. The code is modified from squad.

Acknowledgements

Some codes are modified from CSS, UpDn, squad, and Re-bias. Thanks for their open source.

Code release for General Greedy De-bias Learning

Related tags

Overview

General Greedy De-bias for Dataset Biases

GGD

Biased-MNIST

VQA-CP

Adversarial SQuAD

Acknowledgements

Owner

Using Random Effects to Account for High-Cardinality Categorical Features and Repeated Measures in Deep Neural Networks

Implementation of ResMLP, an all MLP solution to image classification, in Pytorch

Group Activity Recognition with Clustered Spatial Temporal Transformer

Data from "HateCheck: Functional Tests for Hate Speech Detection Models" (Röttger et al., ACL 2021)

Single/multi view image(s) to voxel reconstruction using a recurrent neural network

The authors' official PyTorch SigWGAN implementation

PyTorch implementation of Federated Learning with Non-IID Data, and federated learning algorithms, including FedAvg, FedProx.

Reference models and tools for Cloud TPUs.

Boost learning for GNNs from the graph structure under challenging heterophily settings. (NeurIPS'20)

Codebase for "ProtoAttend: Attention-Based Prototypical Learning."

LAMDA: Label Matching Deep Domain Adaptation

ICLR2021 (Under Review)

This repo uses a combination of logits and feature distillation method to teach the PSPNet model of ResNet18 backbone with the PSPNet model of ResNet50 backbone. All the models are trained and tested on the PASCAL-VOC2012 dataset.

A synthetic texture-invariant dataset for object detection of UAVs

StarGAN v2 - Official PyTorch Implementation (CVPR 2020)

code for paper -- "Seamless Satellite-image Synthesis"

This repository is an implementation of paper : Improving the Training of Graph Neural Networks with Consistency Regularization

Software for Multimodalty 2D+3D Facial Expression Recognition (FER) UI

Official code for article "Expression is enough: Improving traﬀic signal control with advanced traﬀic state representation"

Rule Based Classification Project For Python