From Global to Local: Social Bias Transfer in CLIP

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ramos, Ryan, Hirota, Yusuke, Nakashima, Yuta, Garcia, Noa
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Would Deep Generative Models Amplify Bias in Future Models?
by: Chen, Tianwei, et al.
Published: (2024)

From Descriptive Richness to Bias: Unveiling the Dark Side of Generative Image Caption Enrichment
by: Hirota, Yusuke, et al.
Published: (2024)

Stable Diffusion Exposed: Gender Bias from Prompt to Image
by: Wu, Yankun, et al.
Published: (2023)

Processing and acquisition traces in visual encoders: What does CLIP know about your camera?
by: Ramos, Ryan, et al.
Published: (2025)

SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP
by: Hirota, Yusuke, et al.
Published: (2024)

EMMA: Concept Erasure Benchmark with Comprehensive Semantic Metrics and Diverse Categories
by: Wei, Lu, et al.
Published: (2025)

Resampled Datasets Are Not Enough: Mitigating Societal Bias Beyond Single Attributes
by: Hirota, Yusuke, et al.
Published: (2024)

Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation
by: Hirota, Yusuke, et al.
Published: (2025)

No Annotations for Object Detection in Art through Stable Diffusion
by: Ramos, Patrick, et al.
Published: (2024)

Privacy in Image Datasets: A Case Study on Pregnancy Ultrasounds
by: Lohanimit, Rawisara, et al.
Published: (2026)

Data Leakage in Visual Datasets
by: Ramos, Patrick, et al.
Published: (2025)

Measure Twice, Cut Once: A Semantic-Oriented Approach to Video Temporal Localization with Video LLMs
by: Pang, Zongshang, et al.
Published: (2025)

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

ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation
by: Wang, Jingyun, et al.
Published: (2024)

From Global to Local: Rethinking CLIP Feature Aggregation for Person Re-Identification
by: Zheng, Aotian, et al.
Published: (2026)

FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization
by: Wang, Junyang, et al.
Published: (2022)

Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP
by: Zhang, Zeliang, et al.
Published: (2024)

Is CLIP Cross-Eyed? Revealing and Mitigating Center Bias in the CLIP Family
by: Chew, Oscar, et al.
Published: (2026)

LOTUS: A Leaderboard for Detailed Image Captioning from Quality to Societal Bias and User Preferences
by: Hirota, Yusuke, et al.
Published: (2025)

CLIP-DQA: Blindly Evaluating Dehazed Images from Global and Local Perspectives Using CLIP
by: Zeng, Yirui, et al.
Published: (2025)

ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-training
by: Jiang, Zhouqiang, et al.
Published: (2024)

IPAD-CLIP: Teaching CLIP to Detect Image Local Perceptual Artifacts
by: Wang, Juan, et al.
Published: (2026)

GlocalCLIP: Object-agnostic Global-Local Prompt Learning for Zero-shot Anomaly Detection
by: Ham, Jiyul, et al.
Published: (2024)

Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads
by: Yeo, Wei Jie, et al.
Published: (2025)

Interpretable Debiasing of Vision-Language Models for Social Fairness
by: An, Na Min, et al.
Published: (2026)

CLIP-Loc: Multi-modal Landmark Association for Global Localization in Object-based Maps
by: Matsuzaki, Shigemichi, et al.
Published: (2024)

PANICL: Mitigating Over-Reliance on Single Prompt in Visual In-Context Learning
by: Zhang, Jiahao, et al.
Published: (2025)

VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction
by: Zhang, Jiahao, et al.
Published: (2024)

Explainable Image Recognition via Enhanced Slot-attention Based Classifier
by: Wang, Bowen, et al.
Published: (2024)

CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks
by: Fang, Hao, et al.
Published: (2024)

CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization
by: Xia, Rui, et al.
Published: (2025)

SegDebias: Test-Time Bias Mitigation for ViT-Based CLIP via Segmentation
by: Wu, Fangyu, et al.
Published: (2025)

Enhancing Concept Localization in CLIP-based Concept Bottleneck Models
by: Kazmierczak, Rémi, et al.
Published: (2025)

When Semantics Regulate: Rethinking Patch Shuffle and Internal Bias for Generated Image Detection with CLIP
by: Chu, Beilin, et al.
Published: (2025)

Detecting Visual Triggers in Cannabis Imagery: A CLIP-Based Multi-Labeling Framework with Local-Global Aggregation
by: Lu, Linqi, et al.
Published: (2024)

AnimalMotionCLIP: Embedding motion in CLIP for Animal Behavior Analysis
by: Zhong, Enmin, et al.
Published: (2025)

Revisiting Relevance Feedback for CLIP-based Interactive Image Retrieval
by: Nara, Ryoya, et al.
Published: (2024)

CLIP-Clique: Graph-based Correspondence Matching Augmented by Vision Language Models for Object-based Global Localization
by: Matsuzaki, Shigemichi, et al.
Published: (2024)

Micro-AU CLIP: Fine-Grained Contrastive Learning from Local Independence to Global Dependency for Micro-Expression Action Unit Detection
by: Wei, Jinsheng, et al.
Published: (2026)

Bridging the Task Gap: Multi-Task Adversarial Transferability in CLIP and Its Derivatives
by: Liu, Kuanrong, et al.
Published: (2025)