SCARF: A Semantic Constrained Attention Refinement Network for Semantic Segmentation

Xiaofeng Ding, Chaomin Shen, Zhengping Che, Tieyong Zeng, Yaxin Peng; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 3002-3011

Semantic segmentation has achieved great progress by exploiting the contextual dependencies. In this paper, we propose an end-to-end Semantic Constrained Attention ReFinement (SCARF) network, based on semantic constrained contextual dependencies, to fully utilize the semantic information across different layers. Our novelties lie in the following aspects: Firstly, we present a general framework for capturing the non-local contextual dependencies. Secondly, within the framework, we introduce an efficient Category Attention (CA) block to capture semantic-related context by using the category constraint from coarse segmentation, which reduces the computational complexity from O(n^2) to O(n) for image with n pixels. Thirdly, we overcome the contextual information confusion problem by balancing the non-local contextual dependencies and the local consistency adaptively using a category-wise learning weight. Finally, we fully utilize the multi-scale semantic-related contextual information by refining the segmentation iteratively across layers with semantic constraint. Extensive evaluations demonstrate that our SCARF network significantly improves the segmentation results and achieves superior performance 85.0% mIoU on PASCAL VOC 2012, 55.0% mIoU on PASCAL Context, and 82.1% mIoU on Cityscapes.