mlsanityData to 14 Oct 2026

When SAM Meets Shadow Detection

arXiv 2305.11513 ↗First posted 19 May 2023cs.CVcited by 6

Not on the map. Why?

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.

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

12 of 29 references.

References · 12

  1. 2023Segment Anythingcited by 8,234
  2. 2023Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentationcited by 490
  3. 2023Customized Segment Anything Model for Medical Image Segmentationcited by 280
  4. 2017Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removalcited by 161
  5. 2023Can SAM Segment Anything? When SAM Meets Camouflaged Object Detectioncited by 100
  6. 2023SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anythingcited by 75
  7. 2017Direction-aware Spatial Context Features for Shadow Detectioncited by 56
  8. 2017A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuationcited by 39
  9. 2019Revisiting Shadow Detection: A New Benchmark Dataset for Complex Worldcited by 34
  10. 2021Learning from Synthetic Shadows for Shadow Detection and Removalcited by 27
  11. 2021Fine-Context Shadow Detection using Shadow Removalcited by 9
  12. 2017Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Networkcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 4.

6 papers.

  1. 2024ASAM: Boosting Segment Anything Model with Adversarial Tuningcited by 12
  2. 2024Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Eracited by 7
  3. 2023AdapterShadow: Adapting Segment Anything Model for Shadow Detectioncited by 5
  4. 2023Industrial Segment Anything -- a Case Study in Aircraft Manufacturing, Intralogistics, Maintenance, Repair, and Overhaulcited by 4
  5. 2024SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removalcited by 4
  6. 2024When SAM2 Meets Video Shadow and Mirror Detectioncited by 1