You Never Know: Quantization Induces Inconsistent Biases in Vision-Language Foundation Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916456691662848 |
|---|---|
| author | Slyman, Eric Kanneganti, Anirudh Hong, Sanghyun Lee, Stefan |
| author_facet | Slyman, Eric Kanneganti, Anirudh Hong, Sanghyun Lee, Stefan |
| contents | We study the impact of a standard practice in compressing foundation vision-language models - quantization - on the models' ability to produce socially-fair outputs. In contrast to prior findings with unimodal models that compression consistently amplifies social biases, our extensive evaluation of four quantization settings across three datasets and three CLIP variants yields a surprising result: while individual models demonstrate bias, we find no consistent change in bias magnitude or direction across a population of compressed models due to quantization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20265 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | You Never Know: Quantization Induces Inconsistent Biases in Vision-Language Foundation Models Slyman, Eric Kanneganti, Anirudh Hong, Sanghyun Lee, Stefan Computer Vision and Pattern Recognition Computers and Society Machine Learning We study the impact of a standard practice in compressing foundation vision-language models - quantization - on the models' ability to produce socially-fair outputs. In contrast to prior findings with unimodal models that compression consistently amplifies social biases, our extensive evaluation of four quantization settings across three datasets and three CLIP variants yields a surprising result: while individual models demonstrate bias, we find no consistent change in bias magnitude or direction across a population of compressed models due to quantization. |
| title | You Never Know: Quantization Induces Inconsistent Biases in Vision-Language Foundation Models |
| topic | Computer Vision and Pattern Recognition Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2410.20265 |