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

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

An image base contains 490 images for learning (400 cars and 90 boats), and another 21 images for testingAn image base contains 490 images for learning (400 cars and 90 boats), and another 21 images for testing

WPPNets: Unsupervised CNN Training with Wasserstein Patch Priors for Image Superresolution

Dynamic Attentive Graph Learning for Image Restoration, ICCV2021 [PyTorch Code]

Trains an agent with stochastic policy gradient ascent to solve the Lunar Lander challenge from OpenAI

Transformer in Vision

Spearmint Bayesian optimization codebase

Source code for Acorn, the precision farming rover by Twisted Fields

tensorflow implementation of 'YOLO : Real-Time Object Detection'

Research code for Arxiv paper "Camera Motion Agnostic 3D Human Pose Estimation"

A series of convenience functions to make basic image processing operations such as translation, rotation, resizing, skeletonization, and displaying Matplotlib images easier with OpenCV and Python.

Repository of 3D Object Detection with Pointformer (CVPR2021)

Code Impementation for "Mold into a Graph: Efficient Bayesian Optimization over Mixed Spaces"

Scripts used to make and evaluate OpenAlex's concept tagging model

Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase

[ICLR 2021 Spotlight Oral] "Undistillable: Making A Nasty Teacher That CANNOT teach students", Haoyu Ma, Tianlong Chen, Ting-Kuei Hu, Chenyu You, Xiaohui Xie, Zhangyang Wang

Code for the paper: Sketch Your Own GAN

Codes for AAAI22 paper "Learning to Solve Travelling Salesman Problem with Hardness-Adaptive Curriculum"

Multiple Object Tracking with Yolov5!

Implement of "Training deep neural networks via direct loss minimization" in PyTorch for 0-1 loss