A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation

TL;DR

This paper introduces a GAN-based framework with an adversarial shadow attenuation network to enhance shadow detection accuracy, outperforming state-of-the-art methods while maintaining real-time performance.

Contribution

It presents a novel adversarial training approach combining shadow attenuation with detection, improving accuracy and robustness in shadow detection tasks.

Findings

Significant accuracy improvement on SBU benchmark

State-of-the-art results on cross-dataset UCF test

Real-time detection at 45 fps

Abstract

We propose a novel GAN-based framework for detecting shadows in images, in which a shadow detection network (D-Net) is trained together with a shadow attenuation network (A-Net) that generates adversarial training examples. The A-Net modifies the original training images constrained by a simplified physical shadow model and is focused on fooling the D-Net's shadow predictions. Hence, it is effectively augmenting the training data for D-Net with hard-to-predict cases. The D-Net is trained to predict shadows in both original images and generated images from the A-Net. Our experimental results show that the additional training data from A-Net significantly improves the shadow detection accuracy of D-Net. Our method outperforms the state-of-the-art methods on the most challenging shadow detection benchmark (SBU) and also obtains state-of-the-art results on a cross-dataset task, testing on UCF. Furthermore, the proposed method achieves accurate real-time shadow detection at 45 frames per second.