paper-with-me

홈 › Papers

MAVias: Mitigate any Visual Bias

2024-12-09 · Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou

Mitigating biases in computer vision models is an essential step towards the trustworthiness of artificial intelligence models. Existing bias mitigation methods focus on a small set of predefined biases, limiting their applicability in visual datasets where multiple, possibly unknown biases exist. To address this limitation, we introduce MAVias, an open-set bias mitigation approach leveraging foundation models to discover spurious associations between visual attributes and target classes. MAVias first captures a wide variety of visual features in natural language via a foundation image tagging model, and then leverages a large language model to select those visual features defining the target class, resulting in a set of language-coded potential visual biases. We then translate this set of potential biases into vision-language embeddings and introduce an in-processing bias mitigation approach to prevent the model from encoding information related to them. Our experiments on diverse datasets, including CelebA, Waterbirds, ImageNet, and UrbanCars, show that MAVias effectively detects and mitigates a wide range of biases in visual recognition tasks outperforming current state-of-the-art.

📄 PDF Abstract BibTeX arXiv:2412.06632

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Focus 설명 없음

Similar Papers 제목 키워드 기반

Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation

2022-04-20 · Rebecca S Stone, Nishant Ravikumar, Andrew J Bulpitt, David C Hogg

Deep neural networks are highly susceptible to learning biases in visual data. While various methods have been proposed to mitigate such bias, the majority require explicit knowledge of the biases present in the training…

Face Detection

VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations

2021-04-06 · Archit Rathore, Sunipa Dev, Jeff M. Phillips, Vivek Srikumar 외

Word vector embeddings have been shown to contain and amplify biases in data they are extracted from. Consequently, many techniques have been proposed to identify, mitigate, and attenuate these biases in word representat…

Decision MakingDimensionality ReductionEthicsFairness+1

Understanding Bias in Perceiving Dimensionality Reduction Projections

2025-07-28 · Seoyoung Doh, Hyeon Jeon, Sungbok Shin, Ghulam Jilani Quadri 외 arxiv

Selecting the dimensionality reduction technique that faithfully represents the structure is essential for reliable visual communication and analytics. In reality, however, practitioners favor projections for other attra…

Dimensionality Reduction

Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasing

2025-03-01 · CVPR 2025 1 · Yanjun Li, Zhaoyang Li, Honghui Chen, Lizhi Xu

Video Scene Graph Generation (VidSGG) aims to capture dynamic relationships among entities by sequentially analyzing video frames and integrating visual and semantic information. However, VidSGG is challenged by signific…

Graph GenerationScene Graph GenerationTripletVideo scene graph generation

SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense

2025-10-18 · Yiyang Huang, Liang Shi, Yitian Zhang, Yi Xu 외 arxiv

Large Vision-Language Models (LVLMs) excel in diverse cross-modal tasks. However, object hallucination, where models produce plausible but inaccurate object descriptions, remains a significant challenge. In contrast to p…