Princeton Visual AI Lab

ContextualBias

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

DomainBiasMitigation

gan-debiasing

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

HIVE

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

imagenet-face-obfuscation

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

MQVR

multimodal_dataset_distillation

pointingqa

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

RememberThePast-DatasetDistillation

revise-tool

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

princetonvisualai/revise-tool

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

princetonvisualai/gan-debiasing

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

princetonvisualai/DomainBiasMitigation

princetonvisualai/multimodal_dataset_distillation

princetonvisualai/imagenet-face-obfuscation

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

princetonvisualai/RememberThePast-DatasetDistillation

princetonvisualai/MQVR

princetonvisualai/ContextualBias

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

princetonvisualai/HIVE

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

princetonvisualai/pointingqa

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

princetonvisualai/What-is-Dataset-Distillation-Learning

princetonvisualai/directional-bias-amp

https://arxiv.org/abs/2102.12594

princetonvisualai/imagecaptioning-bias

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

princetonvisualai/SPICE-U

princetonvisualai/conceptmix

princetonvisualai/OverlookedFactors

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

princetonvisualai/HAT

princetonvisualai/overcoming-pretraining-bias

princetonvisualai/geode_dataset

princetonvisualai/gender-artifacts

https://arxiv.org/abs/2206.09191

princetonvisualai/hpe-inductive-prior-tuning

princetonvisualai/imagenetood

princetonvisualai/VLNActionPriors

princetonvisualai/UFOExplainer

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

princetonvisualai/intersectionality

https://arxiv.org/abs/2205.04610

princetonvisualai/pythia

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