paper-with-me

Papers

Multi-Task Learning Using Uncertainty to Weigh Losses for Heterogeneous Face Attribute Estimation

2024-03-01 · Huaqing Yuan, Yi He, Peng Du, Lu Song

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 multitask learning. Experimental results on benchmarks with multiple face attributes show that the proposed approach has superior performance compared to state of the art. Finally, we discuss the bias issues arising from the proposed approach in face attribute estimation and validate its feasibility on edge systems.

📄 PDF Abstract BibTeX arXiv:2403.00561

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeMulti-Task Learning

Similar Papers 제목 키워드 기반

Multi-Loss Weighting with Coefficient of Variations

2020-09-03 · Rick Groenendijk, Sezer Karaoglu, Theo Gevers, Thomas Mensink

Many interesting tasks in machine learning and computer vision are learned by optimising an objective function defined as a weighted linear combination of multiple losses. The final performance is sensitive to choosing t…

Depth EstimationMonocular Depth EstimationMulti-Task LearningSemantic Segmentation

Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics

2017-05-19 · CVPR 2018 6 · Alex Kendall, Yarin Gal, Roberto Cipolla

Numerous deep learning applications benefit from multi-task learning with multiple regression and classification objectives. In this paper we make the observation that the performance of such systems is strongly dependen…

Deep LearningGeneral ClassificationInstance SegmentationMulti-Task Learning+2

Analytical Uncertainty-Based Loss Weighting in Multi-Task Learning

2024-08-15 · Lukas Kirchdorfer, Cathrin Elich, Simon Kutsche, Heiner Stuckenschmidt 외

With the rise of neural networks in various domains, multi-task learning (MTL) gained significant relevance. A key challenge in MTL is balancing individual task losses during neural network training to improve performanc…

Multi-Task Learning

Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multi-Task Learning Perspective

2024-12-27 · Yuanze Li, Chun-Mei Feng, Qilong Wang, Guanglei Yang 외

Human beings can leverage knowledge from relative tasks to improve learning on a primary task. Similarly, multi-task learning methods suggest using auxiliary tasks to enhance a neural network's performance on a specific …

Multi-Task Learning

Upper Comonotonicity and Risk Aggregation under Dependence Uncertainty

2024-06-27 · Corrado De Vecchi, Max Nendel, Jan Streicher

In this paper, we study dependence uncertainty and the resulting effects on tail risk measures, which play a fundamental role in modern risk management. We introduce the notion of a regular dependence measure, defined on…

Management