paper-with-me

Papers

FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models

2024-05-28 · Hanjun Luo, Ziye Deng, Ruizhe Chen, Zuozhu Liu

The rapid development and reduced barriers to entry for Text-to-Image (T2I) models have raised concerns about the biases in their outputs, but existing research lacks a holistic definition and evaluation framework of biases, limiting the enhancement of debiasing techniques. To address this issue, we introduce FAIntbench, a holistic and precise benchmark for biases in T2I models. In contrast to existing benchmarks that evaluate bias in limited aspects, FAIntbench evaluate biases from four dimensions: manifestation of bias, visibility of bias, acquired attributes, and protected attributes. We applied FAIntbench to evaluate seven recent large-scale T2I models and conducted human evaluation, whose results demonstrated the effectiveness of FAIntbench in identifying various biases. Our study also revealed new research questions about biases, including the side-effect of distillation. The findings presented here are preliminary, highlighting the potential of FAIntbench to advance future research aimed at mitigating the biases in T2I models. Our benchmark is publicly available to ensure the reproducibility.

📄 PDF Abstract BibTeX arXiv:2405.17814

Code (1)

astarojth/faintbench-v1 공식 구현 pytorch

Similar Papers 제목 키워드 기반

OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer

2026-04-27 · Boyang Wang, Guangyi Xu, Jiahui Zhang, Zhipeng Tang 외 arxiv

Shot Boundary Detection (SBD) aims to automatically identify shot changes and divide a video into coherent shots. While SBD was widely studied in the literature, existing methods often produce non-interpretable boundarie…

Boundary Detection

VHELM: A Holistic Evaluation of Vision Language Models

2024-10-09 · Tony Lee, Haoqin Tu, Chi Heem Wong, Wenhao Zheng 외

Current benchmarks for assessing vision-language models (VLMs) often focus on their perception or problem-solving capabilities and neglect other critical aspects such as fairness, multilinguality, or toxicity. Furthermor…

Fairness

SAGED: A Holistic Bias-Benchmarking Pipeline for Language Models with Customisable Fairness Calibration

2024-09-17 · Xin Guan, Ze Wang, Nathaniel Demchak, Saloni Gupta 외

The development of unbiased large language models is widely recognized as crucial, yet existing benchmarks fall short in detecting biases due to limited scope, contamination, and lack of a fairness baseline. SAGED(bias) …

BenchmarkingcounterfactualFairnessSentiment Analysis

HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models

2023-04-11 · ICCV 2023 1 · Eslam Mohamed BAKR, Pengzhan Sun, Xiaoqian Shen, Faizan Farooq Khan 외

In recent years, Text-to-Image (T2I) models have been extensively studied, especially with the emergence of diffusion models that achieve state-of-the-art results on T2I synthesis tasks. However, existing benchmarks heav…

FairnessImage GenerationText to Image GenerationText-to-Image Generation

ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation

2024-12-12 · CVPR 2025 1 · Ali Athar, Xueqing Deng, Liang-Chieh Chen

Recent advances in multimodal large language models (MLLMs) have expanded research in video understanding, primarily focusing on high-level tasks such as video captioning and question-answering. Meanwhile, a smaller body…

Phrase GroundingQuestion AnsweringSegmentationSemantic Segmentation+2