透视图(图形)
培训(气象学)
计算机科学
多任务学习
小学(天文学)
心理学
任务(项目管理)
人工智能
工程类
系统工程
地理
物理
气象学
天文
作者
Yuanze Li,Chun-Mei Feng,Qilong Wang,Guanglei Yang,Wangmeng Zuo
标识
DOI:10.1109/tnnls.2024.3462788
摘要
Human beings can leverage knowledge from relative tasks to improve learning on a primary task. Similarly, multitask learning (MTL) methods suggest using auxiliary tasks to enhance a neural network's performance on a specific primary task. However, previous methods often select auxiliary tasks carefully but treat them as secondary during training. The weights assigned to auxiliary losses are typically smaller than the primary loss weight, leading to insufficient training on auxiliary tasks and ultimately failing to support the main task effectively. To address this issue, we propose an uncertainty-based impartial learning method that ensures balanced training across all tasks. In addition, we consider both gradients and uncertainty information during backpropagation to further improve performance on the primary task. Extensive experiments show that our method achieves performance comparable to or better than state-of-the-art approaches. Moreover, our weighting strategy is effective and robust in enhancing the performance of the primary task regardless of the noise auxiliary tasks' pseudolabels.
科研通智能强力驱动
Strongly Powered by AbleSci AI