Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts
This work addresses the problem of improving accuracy in semantic segmentation and boundary detection for computer vision applications, representing a strong specific gain rather than a foundational advancement.
The paper tackles the joint tasks of semantic segmentation and boundary detection by introducing an iterative pyramid context module and spatial gradient fusion, achieving a mean IoU of 81.8% on Cityscapes for segmentation and improving boundary detection by 9.9% in AP and 6.8% in MF(ODS).
In this paper, we present a joint multi-task learning framework for semantic segmentation and boundary detection. The critical component in the framework is the iterative pyramid context module (PCM), which couples two tasks and stores the shared latent semantics to interact between the two tasks. For semantic boundary detection, we propose the novel spatial gradient fusion to suppress nonsemantic edges. As semantic boundary detection is the dual task of semantic segmentation, we introduce a loss function with boundary consistency constraint to improve the boundary pixel accuracy for semantic segmentation. Our extensive experiments demonstrate superior performance over state-of-the-art works, not only in semantic segmentation but also in semantic boundary detection. In particular, a mean IoU score of 81:8% on Cityscapes test set is achieved without using coarse data or any external data for semantic segmentation. For semantic boundary detection, we improve over previous state-of-the-art works by 9.9% in terms of AP and 6:8% in terms of MF(ODS).