princetonvisualai Goto Github PK

contextualbias

[Re] Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias (ML Reproducibility Challenge 2020)

directional-bias-amp

https://arxiv.org/abs/2102.12594

domainbiasmitigation

gan-debiasing

Fair Attribute Classification through Latent Space De-biasing (CVPR 2021)

gender-artifacts

https://arxiv.org/abs/2206.09191

geode_dataset

hat

hive

HIVE: Evaluating the Human Interpretability of Visual Explanations (ECCV 2022)

hpe-inductive-prior-tuning

imagecaptioning-bias

Code for the paper "Understanding and Evaluating Racial Biases in Image Captioning"

imagenet-face-obfuscation

Code for the paper "A Study of Face Obfuscation in ImageNet"

imagenetood

intersectionality

https://arxiv.org/abs/2205.04610

mqvr

multimodal_dataset_distillation

overcoming-pretraining-bias

overlookedfactors

Overlooked Factors in Concept-based Explanations: Dataset Choice, Concept Learnability, and Human Capability (CVPR 2023)

pointingqa

Code for paper "Point and Ask: Incorporating Pointing into Visual Question Answering"

pythia

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

rememberthepast-datasetdistillation

revise-tool

REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets --- https://arxiv.org/abs/2004.07999

spice-u

ufoexplainer

Code for UFO: A unified method for controlling Understandability and Faithfulness Objectives in concept-based explanations for CNNs

vlnactionpriors