Abstract
Partially Supervised Multi-Task Learning (PS-MTL) aims to leverage knowledge across tasks when annotations are incomplete. Existing approaches, however, have largely focused on the simpler setting of homogeneous, dense prediction tasks, leaving the more realistic challenge of learning from structurally diverse tasks unexplored. To this end, we introduce NexusFlow, a novel, lightweight, and plug-and-play framework effective in both settings. NexusFlow introduces a set of surrogate networks with invertible coupling layers to align the latent feature distributions of tasks, creating a unified representation that enables effective knowledge transfer. The coupling layers are bijective, preserving information while mapping features into a shared canonical space. This invertibility avoids representational collapse and enables alignment across structurally different tasks without reducing expressive capacity. We first evaluate NexusFlow on the core challenge of domain-partitioned autonomous driving, where dense map reconstruction and sparse multi-object tracking are supervised in different geographic regions, creating both structural disparity and a strong domain gap. NexusFlow sets a new state-of-the-art result on nuScenes, outperforming strong partially supervised baselines. To demonstrate generality, we further test NexusFlow on NYUv2 using three homogeneous dense prediction tasks, segmentation, depth, and surface normals, as a representative N-task PS-MTL scenario. NexusFlow yields consistent gains across all tasks, confirming its broad applicability.
Abstract (translated)
部分监督多任务学习（PS-MTL）旨在当标注数据不完整时，在不同任务间共享知识。然而，现有的方法主要集中在同质且密集预测任务的简化场景上，而忽略了更为现实的学习挑战：从结构多样化的任务中进行学习。为此，我们引入了NexusFlow框架，这是一个新颖、轻量级且即插即用的框架，适用于上述两种设置。NexusFlow通过引入一组带有可逆耦合层的替代网络来调整各任务的潜在特征分布，从而创建统一表示并实现有效的知识迁移。这些耦合层是双射映射，在将特征映射到共享的标准空间时保留信息。这种可逆性避免了表示塌陷，并允许跨结构不同的任务对齐而不减少表达能力。 我们首先在领域分割的自动驾驶核心挑战上评估NexusFlow，其中密集地图重建和稀疏多对象跟踪分别在一个地理区域中进行监督学习，导致结构差异明显且存在较强的领域差距。NexusFlow在nuScenes数据集上取得了新的最佳结果，超过了强大的部分监督基准模型。 为了展示其通用性，我们进一步使用NYUv2数据集测试了NexusFlow，在该数据集中采用三个同质密集预测任务：分割、深度估计和表面法线作为具有代表性的N任务PS-MTL场景。在所有这些任务中，NexusFlow都取得了持续的改进，证实其广泛的适用性。 总结来说，NexusFlow通过引入可逆耦合层来解决结构化多样化任务中的知识迁移问题，并且已经在多种设置下证明了其有效性与广泛的应用潜力。
URL
https://arxiv.org/abs/2512.06251
