解决机器人感知中任务数据不均衡问题，实现少样本下多任务协同学习。
Multi-Task Learning for Robot Perception with Imbalanced Data
- 利用任务间交互机制，在标签缺失时仍可联合训练多个感知任务。
- 在少量标注数据下，语义分割与深度估计任务性能提升显著。
- 揭示哪些任务能互相促进，适合资源受限的移动机器人部署。
多任务学习已被证明可提升各任务的准确性，对资源有限的机器人尤为重要。然而，当各任务标签数量不均（即数据不平衡）时，因样本不足可能导致性能下降，且移动机器人在复杂环境中难以获取完整标注。本文提出一种可在部分任务缺乏真值标签的情况下仍能学习的方法，并进行了详细分析。研究发现任务间存在相互促进关系：通过将深度等任务输出作为教师网络输入，可有效引导其他任务学习。实验在NYUDv2和Cityscapes数据集上验证了该方法在小样本条件下的有效性，实现了语义分割与深度估计的性能提升。
原文摘要 · Abstract (English)
Multi-task problem solving has been shown to improve the accuracy of the individual tasks, which is an important feature for robots, as they have a limited resource. However, when the number of labels for each task is not equal, namely imbalanced data exist, a problem may arise due to insufficient number of samples, and labeling is not very easy for mobile robots in every environment. We propose a method that can learn tasks even in the absence of the ground truth labels for some of the tasks. We also provide a detailed analysis of the proposed method. An interesting finding is related to the interaction of the tasks. We show a methodology to find out which tasks can improve the performance of other tasks. We investigate this by training the teacher network with the task outputs such as depth as inputs. We further provide empirical evidence when trained with a small amount of data. We use semantic segmentation and depth estimation tasks on different datasets, NYUDv2 and Cityscapes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。