Contour Loss: Boundary-Aware Learning for Salient Object Segmentation
This work addresses the problem of accurately segmenting salient objects in images for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles salient object segmentation by introducing a boundary-aware learning approach with a novel Contour Loss and a hierarchical global attention module, achieving superior performance on six benchmark datasets and real-time speed of 26 fps.
We present a learning model that makes full use of boundary information for salient object segmentation. Specifically, we come up with a novel loss function, i.e., Contour Loss, which leverages object contours to guide models to perceive salient object boundaries. Such a boundary-aware network can learn boundary-wise distinctions between salient objects and background, hence effectively facilitating the saliency detection. Yet the Contour Loss emphasizes on the local saliency. We further propose the hierarchical global attention module (HGAM), which forces the model hierarchically attend to global contexts, thus captures the global visual saliency. Comprehensive experiments on six benchmark datasets show that our method achieves superior performance over state-of-the-art ones. Moreover, our model has a real-time speed of 26 fps on a TITAN X GPU.