paper-with-me

홈 › Papers

SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP

2024-08-19 · Yusuke Hirota, Min-Hung Chen, Chien-Yi Wang, Yuta Nakashima, Yu-Chiang Frank Wang, Ryo Hachiuma

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 societal bias in CLIP. Although previous studies have proposed to debias societal bias through adversarial learning or test-time projecting, our comprehensive study of these works identifies two critical limitations: 1) loss of attribute information when it is explicitly disclosed in the input and 2) use of the attribute annotations during debiasing process. To mitigate societal bias in CLIP and overcome these limitations simultaneously, we introduce a simple-yet-effective debiasing method called SANER (societal attribute neutralizer) that eliminates attribute information from CLIP text features only of attribute-neutral descriptions. Experimental results show that SANER, which does not require attribute annotations and preserves original information for attribute-specific descriptions, demonstrates superior debiasing ability than the existing methods.

📄 PDF Abstract BibTeX arXiv:2408.10202

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeImage GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Hybrid Vision Transformer_GAN Attribute Neutralizer for Mitigating Bias in Chest X_Ray Diagnosis

2026-01-21 · Jobeal Solomon, Ali Mohammed Mansoor Alsahag, Seyed Sahand Mohammadi Ziabari arxiv

Bias in chest X-ray classifiers frequently stems from sex- and age-related shortcuts, leading to systematic underdiagnosis of minority subgroups. Previous pixel-space attribute neutralizers, which rely on convolutional e…

SANeRF-HQ: Segment Anything for NeRF in High Quality

2023-12-03 · CVPR 2024 1 · Yichen Liu, Benran Hu, Chi-Keung Tang, Yu-Wing Tai

Recently, the Segment Anything Model (SAM) has showcased remarkable capabilities of zero-shot segmentation, while NeRF (Neural Radiance Fields) has gained popularity as a method for various 3D problems beyond novel view …

NeRFNovel View SynthesisObjectObject Localization+3

Spatial Annealing for Efficient Few-shot Neural Rendering

2024-06-12 · Yuru Xiao, Deming Zhai, Wenbo Zhao, Kui Jiang 외

Neural Radiance Fields (NeRF) with hybrid representations have shown impressive capabilities for novel view synthesis, delivering high efficiency. Nonetheless, their performance significantly drops with sparse input view…

NeRFNeural RenderingNovel View Synthesis

Uncurated Image-Text Datasets: Shedding Light on Demographic Bias

2023-04-06 · CVPR 2023 1 · Noa Garcia, Yusuke Hirota, Yankun Wu, Yuta Nakashima

The increasing tendency to collect large and uncurated datasets to train vision-and-language models has raised concerns about fair representations. It is known that even small but manually annotated datasets, such as MSC…

Image CaptioningImage GenerationText to Image GenerationText-to-Image Generation

Improving Resistance to Noisy Label Fitting by Reweighting Gradient in SAM

2024-11-26 · Hoang-Chau Luong, Thuc Nguyen-Quang, Minh-Triet Tran

Noisy labels pose a substantial challenge in machine learning, often resulting in overfitting and poor generalization. Sharpness-Aware Minimization (SAM), as demonstrated in Foret et al. (2021), improves generalization o…