Tuning computer vision models with task rewards

AS Pinto, A Kolesnikov, Y Shi… - … on Machine Learning, 2023 - proceedings.mlr.press
Misalignment between model predictions and intended usage can be detrimental for the
deployment of computer vision models. The issue is exacerbated when the task involves …
被引用次数：26 相关文章

Tuning computer vision models with task rewards

AS Pinto, A Kolesnikov, Y Shi, L Beyer… - arXiv preprint arXiv …, 2023 - arxiv.org
Misalignment between model predictions and intended usage can be detrimental for the
deployment of computer vision models. The issue is exacerbated when the task involves …

Tuning computer vision models with task rewards

AS Pinto, A Kolesnikov, Y Shi, L Beyer… - Proceedings of the 40th …, 2023 - dl.acm.org
Misalignment between model predictions and intended usage can be detrimental for the
deployment of computer vision models. The issue is exacerbated when the task involves …

Tuning Computer Vision Models With Task Rewards

AS Pinto, A Kolesnikov, Y Shi, L Beyer, X Zhai - openreview.net
Misalignment between model predictions and intended usage can be detrimental for the
deployment of computer vision models. The issue is exacerbated when the task involves …