# When SAM Meets Shadow Detection

arXiv: https://arxiv.org/abs/2305.11513 · HTML: https://mlsanity.com/paper/2305.11513/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 19 May 2023.

## Builds on (most cited first, 12 of 12)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [Customized Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.13785/) (2023)
- [Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal](https://mlsanity.com/paper/1712.02478/) (2017)
- [Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection](https://mlsanity.com/paper/2304.04709/) (2023)
- [SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything](https://mlsanity.com/paper/2304.06022/) (2023)
- [Direction-aware Spatial Context Features for Shadow Detection](https://mlsanity.com/paper/1712.04142/) (2017)
- [A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation](https://mlsanity.com/paper/1712.01361/) (2017)
- [Revisiting Shadow Detection: A New Benchmark Dataset for Complex World](https://mlsanity.com/paper/1911.06998/) (2019)
- [Learning from Synthetic Shadows for Shadow Detection and Removal](https://mlsanity.com/paper/2101.01713/) (2021)
- [Fine-Context Shadow Detection using Shadow Removal](https://mlsanity.com/paper/2109.09609/) (2021)
- [Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network](https://mlsanity.com/paper/1709.09283/) (2017)

## Built on by (most cited first, 6 of 6)

- [ASAM: Boosting Segment Anything Model with Adversarial Tuning](https://mlsanity.com/paper/2405.00256/) (2024)
- [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)
- [AdapterShadow: Adapting Segment Anything Model for Shadow Detection](https://mlsanity.com/paper/2311.08891/) (2023)
- [Industrial Segment Anything -- a Case Study in Aircraft Manufacturing, Intralogistics, Maintenance, Repair, and Overhaul](https://mlsanity.com/paper/2307.12674/) (2023)
- [SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal](https://mlsanity.com/paper/2409.07041/) (2024)
- [When SAM2 Meets Video Shadow and Mirror Detection](https://mlsanity.com/paper/2412.19293/) (2024)

## Abstract (arXiv)

As a promptable generic object segmentation model, segment anything model (SAM) has recently attracted significant attention, and also demonstrates its powerful performance. Nevertheless, it still meets its Waterloo when encountering several tasks, e.g., medical image segmentation, camouflaged object detection, etc. In this report, we try SAM on an unexplored popular task: shadow detection. Specifically, four benchmarks were chosen and evaluated with widely used metrics. The experimental results show that the performance for shadow detection using SAM is not satisfactory, especially when comparing with the elaborate models. Code is available at https://github.com/LeipingJie/SAMSh.