all AI news
Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models. (arXiv:2104.08666v2 [cs.CL] UPDATED)
May 23, 2022, 1:12 a.m. | Tejas Srinivasan, Yonatan Bisk
cs.CL updates on arXiv.org arxiv.org
Numerous works have analyzed biases in vision and pre-trained language models
individually - however, less attention has been paid to how these biases
interact in multimodal settings. This work extends text-based bias analysis
methods to investigate multimodal language models, and analyzes intra- and
inter-modality associations and biases learned by these models. Specifically,
we demonstrate that VL-BERT (Su et al., 2020) exhibits gender biases, often
preferring to reinforce a stereotype over faithfully describing the visual
scene. We demonstrate these findings on …
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
IT Data Engineer
@ Procter & Gamble | BUCHAREST OFFICE
Data Engineer (w/m/d)
@ IONOS | Deutschland - Remote
Staff Data Science Engineer, SMAI
@ Micron Technology | Hyderabad - Phoenix Aquila, India
Academically & Intellectually Gifted Teacher (AIG - Elementary)
@ Wake County Public School System | Cary, NC, United States