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

arXiv: https://arxiv.org/abs/1712.01361 · HTML: https://mlsanity.com/paper/1712.01361/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2017.

## Built on by (most cited first, 30 of 39)

- [Camouflaged Object Segmentation with Distraction Mining](https://mlsanity.com/paper/2104.10475/) (2021)
- [Explicit Visual Prompting for Low-Level Structure Segmentations](https://mlsanity.com/paper/2303.10883/) (2023)
- [SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More](https://mlsanity.com/paper/2408.04579/) (2024)
- [Zero-shot Object Counting](https://mlsanity.com/paper/2303.02001/) (2023)
- [From Shadow Generation to Shadow Removal](https://mlsanity.com/paper/2103.12997/) (2021)
- [SAM Fails to Segment Anything? -- SAM-Adapter: Adapting SAM in Underperformed Scenes: Camouflage, Shadow, Medical Image Segmentation, and More](https://mlsanity.com/paper/2304.09148/) (2023)
- [Generating Representative Samples for Few-Shot Classification](https://mlsanity.com/paper/2205.02918/) (2022)
- [Progressive Semantic Segmentation](https://mlsanity.com/paper/2104.03778/) (2021)
- [Triple-cooperative Video Shadow Detection](https://mlsanity.com/paper/2103.06533/) (2021)
- [Instance Shadow Detection with A Single-Stage Detector](https://mlsanity.com/paper/2207.04614/) (2022)
- [SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels](https://mlsanity.com/paper/2308.12064/) (2023)
- [OmniSR: Shadow Removal under Direct and Indirect Lighting](https://mlsanity.com/paper/2410.01719/) (2024)
- [Towards Diverse Binary Segmentation via A Simple yet General Gated Network](https://mlsanity.com/paper/2303.10396/) (2023)
- [Explicit Visual Prompting for Universal Foreground Segmentations](https://mlsanity.com/paper/2305.18476/) (2023)
- [Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training](https://mlsanity.com/paper/2206.08801/) (2022)
- [Beyond Pixels: Semi-Supervised Semantic Segmentation with a Multi-scale Patch-based Multi-Label Classifier](https://mlsanity.com/paper/2407.04036/) (2024)
- [SDDNet: Style-guided Dual-layer Disentanglement Network for Shadow Detection](https://mlsanity.com/paper/2308.08935/) (2023)
- [Test-Time Intensity Consistency Adaptation for Shadow Detection](https://mlsanity.com/paper/2410.07695/) (2024)
- [Progressive Glass Segmentation](https://mlsanity.com/paper/2209.02280/) (2022)
- [Fine-Context Shadow Detection using Shadow Removal](https://mlsanity.com/paper/2109.09609/) (2021)
- [Learning Shadow Correspondence for Video Shadow Detection](https://mlsanity.com/paper/2208.00150/) (2022)
- [Zero-Shot Object Counting with Language-Vision Models](https://mlsanity.com/paper/2309.13097/) (2023)
- [Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Era](https://mlsanity.com/paper/2409.02108/) (2024)
- [SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation, Shadow Detection, and Medical Image Segmentation](https://mlsanity.com/paper/2511.19425/) (2025)
- [When SAM Meets Shadow Detection](https://mlsanity.com/paper/2305.11513/) (2023)
- [Temporal Feature Warping for Video Shadow Detection](https://mlsanity.com/paper/2107.14287/) (2021)
- [AdapterShadow: Adapting Segment Anything Model for Shadow Detection](https://mlsanity.com/paper/2311.08891/) (2023)
- [Shadow Removal Refinement via Material-Consistent Shadow Edges](https://mlsanity.com/paper/2409.06848/) (2024)
- [MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis](https://mlsanity.com/paper/2412.02635/) (2024)
- [SwinShadow: Shifted Window for Ambiguous Adjacent Shadow Detection](https://mlsanity.com/paper/2408.03521/) (2024)

## Abstract (arXiv)

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.