collaborators

5 papers

cs.CV2025

Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation

Yusuke Hirota, Ryo Hachiuma, Boyi Li +9

Gender bias in vision-language foundation models (VLMs) raises concerns about their safe deployment and is typically evaluated using benchmarks with gender annotations on real-worl…

cs.CV2025

LOTUS: A Leaderboard for Detailed Image Captioning from Quality to Societal Bias and User Preferences

Yusuke Hirota, Boyi Li, Ryo Hachiuma +7

Large Vision-Language Models (LVLMs) have transformed image captioning, shifting from concise captions to detailed descriptions. We introduce LOTUS, a leaderboard for evaluating de…

cs.CV2025

SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP

Yusuke Hirota, Min-Hung Chen, Chien-Yi Wang +3

Large-scale vision-language models, such as CLIP, are known to contain societal bias regarding protected attributes (e.g., gender, age). This paper aims to address the problems of…

cs.CV2024

Resampled Datasets Are Not Enough: Mitigating Societal Bias Beyond Single Attributes

Yusuke Hirota, Jerone T. A. Andrews, Dora Zhao +4

We tackle societal bias in image-text datasets by removing spurious correlations between protected groups and image attributes. Traditional methods only target labeled attributes,…

cs.CV2024

From Descriptive Richness to Bias: Unveiling the Dark Side of Generative Image Caption Enrichment

Yusuke Hirota, Ryo Hachiuma, Chao-Han Huck Yang +1

Large language models (LLMs) have enhanced the capacity of vision-language models to caption visual text. This generative approach to image caption enrichment further makes textual…