Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning

arXiv:2403.10252v1 Announce Type: new
Abstract: In this study, we address the intricate challenge of multi-task dense prediction, encompassing tasks such as semantic segmentation, depth estimation, and surface normal estimation, particularly when dealing with partially annotated data (MTPSL). The complexity arises from the absence of complete task labels for each training image. Given the inter-related nature of these pixel-wise dense tasks, our focus is on mining and capturing cross-task relationships. Existing solutions typically rely on learning global image representations for global …

abstract annotated data arxiv challenge complexity contrast cs.cv data distribution labels normal novel prediction segmentation semantic study supervised learning surface tasks type