A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Nair, Rahul, Tokas, Bhanu, Kerner, Hannah
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917447912652800
author Nair, Rahul
Tokas, Bhanu
Kerner, Hannah
author_facet Nair, Rahul
Tokas, Bhanu
Kerner, Hannah
contents When we train models on biased datasets, they not only reproduce data biases, but can worsen them at test time - a phenomenon called bias amplification. Many of the current bias amplification metrics (e.g., BA (MALS), DPA) measure bias amplification only in classification datasets. These metrics are ineffective for image captioning datasets, as they cannot capture the language semantics of a caption. Recent work introduced Leakage in Captioning (LIC), a language-aware bias amplification metric that understands caption semantics. However, LIC has a crucial limitation: it cannot identify the source of bias amplification in captioning models. We propose Directional Bias Amplification in Captioning (DBAC), a language-aware and directional metric that can identify when captioning models amplify biases. DBAC has two more improvements over LIC: (1) it is less sensitive to sentence encoders (a hyperparameter in language-aware metrics), and (2) it provides a more accurate estimate of bias amplification in captions. Our experiments on gender and race attributes in the COCO captions dataset show that DBAC is the only reliable metric to measure bias amplification in captions.
format Preprint
id arxiv_https___arxiv_org_abs_2503_07878
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions
Nair, Rahul
Tokas, Bhanu
Kerner, Hannah
Computer Vision and Pattern Recognition
Artificial Intelligence
When we train models on biased datasets, they not only reproduce data biases, but can worsen them at test time - a phenomenon called bias amplification. Many of the current bias amplification metrics (e.g., BA (MALS), DPA) measure bias amplification only in classification datasets. These metrics are ineffective for image captioning datasets, as they cannot capture the language semantics of a caption. Recent work introduced Leakage in Captioning (LIC), a language-aware bias amplification metric that understands caption semantics. However, LIC has a crucial limitation: it cannot identify the source of bias amplification in captioning models. We propose Directional Bias Amplification in Captioning (DBAC), a language-aware and directional metric that can identify when captioning models amplify biases. DBAC has two more improvements over LIC: (1) it is less sensitive to sentence encoders (a hyperparameter in language-aware metrics), and (2) it provides a more accurate estimate of bias amplification in captions. Our experiments on gender and race attributes in the COCO captions dataset show that DBAC is the only reliable metric to measure bias amplification in captions.
title A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.07878