all AI news
Multi-Task Learning Using Uncertainty to Weigh Losses for Heterogeneous Face Attribute Estimation
March 4, 2024, 5:45 a.m. | Huaqing Yuan, Yi He, Peng Du, Lu Song
cs.CV updates on arXiv.org arxiv.org
Abstract: Face images contain a wide variety of attribute information. In this paper, we propose a generalized framework for joint estimation of ordinal and nominal attributes based on information sharing. We tackle the correlation problem between heterogeneous attributes using hard parameter sharing of shallow features, and trade-off multiple loss functions by considering homoskedastic uncertainty for each attribute estimation task. This leads to optimal estimation of multiple attributes of the face and reduces the training cost of …
abstract arxiv correlation cs.ai cs.cv face framework generalized images information losses multi-task learning ordinal paper type uncertainty
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Business Data Scientist, gTech Ads
@ Google | Mexico City, CDMX, Mexico
Lead, Data Analytics Operations
@ Zocdoc | Pune, Maharashtra, India