提升视觉密集预测的多任务学习方法，改善任务间一致性与训练平衡。
Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization
- 采用视觉变压器+任务专用解码器，增强跨任务几何与预测一致性。
- 动态平衡损失，优先处理困难任务，在两个数据集上达到新最好性能。
- 适合需要高精度密集预测的场景，如医学图像分割、自动驾驶感知。
多任务学习（MTL）在计算机视觉的密集预测任务中具有显著优势，能减少训练与推理时间，并通过任务间的交互提升准确率。然而现有方法存在跨任务交互不优、任务预测缺乏几何与预测一致性的问题，且损失加权策略未能应对训练过程中任务演化的差异性。为此，本文提出一种专为密集视觉任务设计的先进MTL模型。该模型结合先进的视觉变压器与任务特定解码器，引入回溯机制以强化跨任务的几何与预测特征一致性；同时提出一种新型动态任务平衡方法，将任务损失投影至统一尺度并优先优化较难任务。大量实验表明，该方法在两个基准数据集上均实现新最优表现。代码已开源：https://github.com/Klodivio355/MT-CP。
原文摘要 · Abstract (English)
Multi-Task Learning (MTL) involves the concurrent training of multiple tasks, offering notable advantages for dense prediction tasks in computer vision. MTL not only reduces training and inference time as opposed to having multiple single-task models, but also enhances task accuracy through the interaction of multiple tasks. However, existing methods face limitations. They often rely on suboptimal cross-task interactions, resulting in task-specific predictions with poor geometric and predictive coherence. In addition, many approaches use inadequate loss weighting strategies, which do not address the inherent variability in task evolution during training. To overcome these challenges, we propose an advanced MTL model specifically designed for dense vision tasks. Our model leverages state-of-the-art vision transformers with task-specific decoders. To enhance cross-task coherence, we introduce a trace-back method that improves both cross-task geometric and predictive features. Furthermore, we present a novel dynamic task balancing approach that projects task losses onto a common scale and prioritizes more challenging tasks during training. Extensive experiments demonstrate the superiority of our method, establishing new state-of-the-art performance across two benchmark datasets. The code is available at:https://github.com/Klodivio355/MT-CP
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。