Direction-aware Spatial Context Features for Shadow Detection

Shadow detection is a fundamental and challenging task, since it requires an understanding of global image semantics and there are various backgrounds around shadows. This paper presents a novel network for shadow detection by analyzing image context in a direction-aware manner. To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN. By learning these weights through training, we can recover direction-aware spatial context (DSC) for detecting shadows. This design is developed into the DSC module and embedded in a CNN to learn DSC features at different levels. Moreover, a weighted cross entropy loss is designed to make the training more effective. We employ two common shadow detection benchmark datasets and perform various experiments to evaluate our network. Experimental results show that our network outperforms state-of-the-art methods and achieves 97% accuracy and 38% reduction on balance error rate.

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
RGB Salient Object Detection SBU DSC Balanced Error Rate 5.59 # 2
Shadow Detection SBU DSC BER 5.59 # 5
RGB Salient Object Detection UCF DSC Balanced Error Rate 8.10 # 4

Results from Other Papers

Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
RGB Salient Object Detection ISTD DSC Balanced Error Rate 8.24 # 5


No methods listed for this paper. Add relevant methods here