Publications

Publications

Google Scholar

Papers

• SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP
  Yusuke Hirota, Min-Hung Chen, Chien-Yi Wang, Yuta Nakashima, Yu-Chiang Frank Wang, Ryo Hachiuma
  ICLR 2025

• Resampled Datasets Are Not Enough: Mitigating Societal Bias Beyond Single Attributes
  Yusuke Hirota, Jerone T. A. Andrews, Dora Zhao, Orestis Papakyriakopoulos, Apostolos Modas, Yuta Nakashima, Alice Xiang
  EMNLP 2024 (main track)

• From Descriptive Richness to Bias: Unveiling the Dark Side of Generative Image Caption Enrichment
  Yusuke Hirota,  Ryo Hachiuma, Chao-Han Huck Yang, Yuta Nakashima
  EMNLP 2024 (main track)

• Would Deep Generative Models Amplify Bias in Future Models?
  Tianwei Chen, Yusuke Hirota, Mayu Otani, Noa Garcia, Yuta Nakashima
  CVPR 2024

• Model-Agnostic Gender Debiased Image Captioning
  Yusuke Hirota, Yuta Nakashima, Noa Garcia
  CVPR 2023

• Uncurated Image-Text Datasets: Shedding Light on Demographic Bias
  Noa Garcia, Yusuke Hirota, Yankun Wu, Yuta Nakashima
  CVPR 2023, Highlight

• Quantifying Societal Bias Amplification in Image Captioning
  Yusuke Hirota, Yuta Nakashima, Noa Garcia
  CVPR 2022, Oral

• Gender and Racial Bias in Visual Question Answering Datasets
  Yusuke Hirota, Yuta Nakashima, Noa Garcia
  ACM FAccT 2022

• Visual Question Answering with Textual Representations for Images
  Yusuke Hirota, Noa Garcia, Mayu Otani, Chenhui Chu, Yuta Nakashima, Ittetsu Taniguchi, Takao Onoye
  ICCV CLVL 2021