Direction-aware Spatial Context Features for Shadow Detection

TL;DR

This paper introduces a direction-aware spatial context network for shadow detection, leveraging a novel attention mechanism within a spatial RNN to improve accuracy and reduce errors.

Contribution

It proposes a new direction-aware attention mechanism integrated into a CNN for enhanced shadow detection performance.

Findings

Achieves 97% accuracy on benchmark datasets.

Reduces balance error rate by 38%.

Outperforms existing state-of-the-art methods.

Abstract

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.