[CVPR2019]Learning Not to Learn : An adversarial method to train deep neural networks with biased data

Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021 Oral.

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Class Activation Mapping

Tensorflow implementation of S4L: Self-Supervised Semi-Supervised Learning

Hyperspherical Prototype Networks

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

[ICLR 2021 Spotlight] Code release for "Long-tailed Recognition by Routing Diverse Distribution-Aware Experts."

Simple data balancing baselines for worst-group-accuracy benchmarks.

An Investigation of Why Overparameterization Exacerbates Spurious Correlations

A curated list of DATASETS, CODEBASES and PAPERS on Multi-Task Learning (MTL), from Machine Learning perspective.

Pytorch reimplementation for "Gradient Surgery for Multi-Task Learning"

Code for "Gradient Surgery for Multi-Task Learning"

[ICCV 2021] Released code for Causal Attention for Unbiased Visual Recognition

[ICCV 2021] Influence-balanced Loss for Imbalanced Visual Classification

Code for our paper: Samuel and Chechik, "Distributional Robustness Loss for Long-tail Learning"

ICCV2021/2019/2017 论文/代码/解读/直播合集，极市团队整理

Methods of training NLP models to ignored biased strategies

REPresentAtion bIas Removal (REPAIR) of datasets

Combating hidden stratification with GEORGE

Distributionally robust neural networks for group shifts

Gradient Starvation: A Learning Proclivity in Neural Networks

NeurIPS 2019 Paper: RUBi : Reducing Unimodal Biases for Visual Question Answering

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

ICML'19 How does Disagreement Help Generalization against Label Corruption?