用任务专属归一化简化多任务模型，性能不降反升。
Simplifying Multi-Task Architectures Through Task-Specific Normalization
- 用任务特异性归一化替代复杂模块，轻量高效
- 在多个数据集上表现媲美甚至超越主流架构
- 可解释的门控机制，揭示任务间容量分配规律
多任务学习旨在通过任务间共享知识提升泛化能力与参数效率，但资源平衡与干扰抑制仍是难题。现有架构常引入复杂的任务专用模块或路由机制，增加计算开销。本文发现仅通过任务特异性归一化即可有效应对诸多挑战。将共享归一化替换为任务特异性版本已能取得竞争力表现，质疑复杂设计的必要性。在此基础上，提出轻量级任务特异性Sigmoid批归一化（TSσBN），使各任务能软性分配网络容量，同时完全共享特征提取器。该方法在CNN与Transformer上均提升稳定性，在NYUv2、Cityscapes、CelebA和PascalContext上达到或超越现有性能，且参数开销极低。其学习到的门控机制还提供了分析多任务动态的自然框架，可解释地揭示容量分配、滤波器专业化及任务关系。结果表明，复杂多任务架构可能并非必需，任务特异性归一化是一种简单、可解释且高效的替代方案。
原文摘要 · Abstract (English)
Multi-task learning (MTL) aims to leverage shared knowledge across tasks to improve generalization and parameter efficiency, yet balancing resources and mitigating interference remain open challenges. Architectural solutions often introduce elaborate task-specific modules or routing schemes, increasing complexity and overhead. In this work, we show that normalization layers alone are sufficient to address many of these challenges. Simply replacing shared normalization with task-specific variants already yields competitive performance, questioning the need for complex designs. Building on this insight, we propose Task-Specific Sigmoid Batch Normalization (TS$σ$BN), a lightweight mechanism that enables tasks to softly allocate network capacity while fully sharing feature extractors. TS$σ$BN improves stability across CNNs and Transformers, matching or exceeding performance on NYUv2, Cityscapes, CelebA, and PascalContext, while remaining highly parameter-efficient. Moreover, its learned gates provide a natural framework for analyzing MTL dynamics, offering interpretable insights into capacity allocation, filter specialization, and task relationships. Our findings suggest that complex MTL architectures may be unnecessary and that task-specific normalization offers a simple, interpretable, and efficient alternative.
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。