用任务原型提升部分标注下的多任务学习鲁棒性
Task Prototype-Based Knowledge Retrieval for Multi-Task Learning from Partially Annotated Data
- 构建任务原型捕捉特征，避免依赖未标注任务预测
- 引入关联知识生成损失，确保原型准确表征任务差异
- 适合标注不全的工业级多任务场景，如自动驾驶
多任务学习在自动驾驶、机器人等实际应用中至关重要，但完全标注所有任务数据成本过高。现有部分标注多任务学习方法依赖未标注任务的预测结果，难以建立可靠的任务关联，易引发负迁移和性能下降。为此，本文提出一种基于原型的知识检索框架，不依赖未标注任务的预测。该框架包含两个核心组件：(1) 任务原型嵌入，用于表征任务特性和量化任务关联；(2) 知识检索变换器，根据任务关联自适应优化特征表示。为确保原型稳定捕捉任务特征，我们设计了关联知识生成（AKG）损失。大量实验验证了该框架的有效性，即使仅部分任务有标注，也能实现鲁棒的多任务学习。
原文摘要 · Abstract (English)
Multi-task learning (MTL) is critical in real-world applications such as autonomous driving and robotics, enabling simultaneous handling of diverse tasks. However, obtaining fully annotated data for all tasks is impractical due to labeling costs. Existing methods for partially labeled MTL typically rely on predictions from unlabeled tasks, making it difficult to establish reliable task associations and potentially leading to negative transfer and suboptimal performance. To address these issues, we propose a prototype-based knowledge retrieval framework that achieves robust MTL instead of relying on predictions from unlabeled tasks. Our framework consists of two key components: (1) a task prototype embedding task-specific characteristics and quantifying task associations, and (2) a knowledge retrieval transformer that adaptively refines feature representations based on these associations. To achieve this, we introduce an association knowledge generating (AKG) loss to ensure the task prototype consistently captures task-specific characteristics. Extensive experiments demonstrate the effectiveness of our framework, highlighting its potential for robust multi-task learning, even when only a subset of tasks is annotated.
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。