Imagen de Portada

The Bias of Harmful Label Associations in Vision-Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hazirbas, Caner, Sun, Alicia, Efroni, Yonathan, Ibrahim, Mark
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
por: Al-Tahan, Haider, et al.
Publicado: (2024)

Pathological Truth Bias in Vision-Language Models
por: Thube, Yash
Publicado: (2025)

Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
por: Zhu, Xingyu, et al.
Publicado: (2024)

Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs
por: Tan, Xuwei, et al.
Publicado: (2026)

When are Lemons Purple? The Concept Association Bias of Vision-Language Models
por: Yamada, Yutaro, et al.
Publicado: (2022)

Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals
por: Howard, Phillip, et al.
Publicado: (2024)

Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models
por: Zhu, Beier, et al.
Publicado: (2023)

Egocentric Bias in Vision-Language Models
por: Wang, Maijunxian, et al.
Publicado: (2026)

Investigating Spatial Attention Bias in Vision-Language Models
por: Chaudhary, Aryan, et al.
Publicado: (2025)

Benchmarking and Mitigating MCQA Selection Bias of Large Vision-Language Models
por: Atabuzzaman, Md., et al.
Publicado: (2025)

Identifying and Mitigating Position Bias of Multi-image Vision-Language Models
por: Tian, Xinyu, et al.
Publicado: (2025)

Bias Redistribution in Visual Machine Unlearning: Does Forgetting One Group Harm Another?
por: Haruna, Yunusa, et al.
Publicado: (2026)

Beyond-Labels: Advancing Open-Vocabulary Segmentation With Vision-Language Models
por: Rahman, Muhammad Atta ur, et al.
Publicado: (2025)

Robustness of Vision Language Models Against Split-Image Harmful Input Attacks
por: Rashid, Md Rafi Ur, et al.
Publicado: (2026)

GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models
por: Huang, Zhaohong, et al.
Publicado: (2025)

debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias
por: Sasse, Kuleen, et al.
Publicado: (2024)

Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization
por: Li, Jiaqi, et al.
Publicado: (2026)

Beyond the Vision Encoder: Identifying and Mitigating Spatial Bias in Large Vision-Language Models
por: Zhu, Yingjie, et al.
Publicado: (2025)

Joint Vision-Language Social Bias Removal for CLIP
por: Zhang, Haoyu, et al.
Publicado: (2024)

Intrinsic Gradient Suppression for Label-Noise Prompt Tuning in Vision-Language Models
por: Li, Jiayu, et al.
Publicado: (2026)

SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language Models
por: Zou, Shu, et al.
Publicado: (2025)

MEBench: A Novel Benchmark for Understanding Mutual Exclusivity Bias in Vision-Language Models
por: Thai, Anh, et al.
Publicado: (2025)

Uncovering Bias in Large Vision-Language Models with Counterfactuals
por: Howard, Phillip, et al.
Publicado: (2024)

Vision-Language Models are Strong Noisy Label Detectors
por: Wei, Tong, et al.
Publicado: (2024)

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks
por: Wang, Han, et al.
Publicado: (2024)

Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias by Generating Realistic Dermoscopic Images
por: Munia, Nusrat, et al.
Publicado: (2025)

VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
por: Huang, Jen-tse, et al.
Publicado: (2025)

Freeze and Reveal: Exposing Modality Bias in Vision-Language Models
por: Kavuri, Vivek Hruday, et al.
Publicado: (2025)

NLPrompt: Noise-Label Prompt Learning for Vision-Language Models
por: Pan, Bikang, et al.
Publicado: (2024)

Tuning Vision-Language Models with Candidate Labels by Prompt Alignment
por: Zhang, Zhifang, et al.
Publicado: (2024)

Label Propagation for Zero-shot Classification with Vision-Language Models
por: Stojnić, Vladan, et al.
Publicado: (2024)

Sanitizing Manufacturing Dataset Labels Using Vision-Language Models
por: Mahjourian, Nazanin, et al.
Publicado: (2025)

Visual Cues of Gender and Race are Associated with Stereotyping in Vision-Language Models
por: Lee, Messi H. J., et al.
Publicado: (2025)

Scaling Pre-training to One Hundred Billion Data for Vision Language Models
por: Wang, Xiao, et al.
Publicado: (2025)

Zero-Shot Product Attribute Labeling with Vision-Language Models: A Three-Tier Evaluation Framework
por: Shukla, Shubham, et al.
Publicado: (2026)

SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models
por: Miller, Kevin, et al.
Publicado: (2025)

Failures to Surface Harmful Contents in Video Large Language Models
por: Cao, Yuxin, et al.
Publicado: (2025)

GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing
por: Xiao, Yisong, et al.
Publicado: (2024)

Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathology
por: Liu, Pei, et al.
Publicado: (2024)

BiasICL: In-Context Learning and Demographic Biases of Vision Language Models
por: Xu, Sonnet, et al.
Publicado: (2025)