# SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels

arXiv: https://arxiv.org/abs/2308.12064 · HTML: https://mlsanity.com/paper/2308.12064/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 83 references that are in the map.
- First posted on arXiv 23 Aug 2023.

## Builds on (most cited first, 30 of 42)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (2017)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [Joint Optimization Framework for Learning with Noisy Labels](https://mlsanity.com/paper/1803.11364/) (2018)
- [Probabilistic End-to-end Noise Correction for Learning with Noisy Labels](https://mlsanity.com/paper/1903.07788/) (2019)
- [Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal](https://mlsanity.com/paper/1712.02478/) (2017)
- [Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion](https://mlsanity.com/paper/1902.03680/) (2019)
- [Deep Self-Learning From Noisy Labels](https://mlsanity.com/paper/1908.02160/) (2019)
- [Learning From Noisy Large-Scale Datasets With Minimal Supervision](https://mlsanity.com/paper/1701.01619/) (2017)
- [Webly Supervised Learning of Convolutional Networks](https://mlsanity.com/paper/1505.01554/) (2015)
- [Masking: A New Perspective of Noisy Supervision](https://mlsanity.com/paper/1805.08193/) (2018)
- [Curriculum Loss: Robust Learning and Generalization against Label Corruption](https://mlsanity.com/paper/1905.10045/) (2019)
- [Learning to Self-Train for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1906.00562/) (2019)
- [A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation](https://mlsanity.com/paper/2104.07256/) (2021)
- [Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks](https://mlsanity.com/paper/1706.00038/) (2017)
- [Adaptive Early-Learning Correction for Segmentation from Noisy Annotations](https://mlsanity.com/paper/2110.03740/) (2021)
- [Direction-aware Spatial Context Features for Shadow Detection and Removal](https://mlsanity.com/paper/1805.04635/) (2018)
- [Disentangling Human Error from the Ground Truth in Segmentation of Medical Images](https://mlsanity.com/paper/2007.15963/) (2020)

## Built on by (most cited first, 19 of 19)

- [OmniSR: Shadow Removal under Direct and Indirect Lighting](https://mlsanity.com/paper/2410.01719/) (2024)
- [Spider: A Unified Framework for Context-dependent Concept Segmentation](https://mlsanity.com/paper/2405.01002/) (2024)
- [Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes](https://mlsanity.com/paper/2412.01240/) (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)
- [Timeline and Boundary Guided Diffusion Network for Video Shadow Detection](https://mlsanity.com/paper/2408.11785/) (2024)
- [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)
- [S-EO: A Large-Scale Dataset for Geometry-Aware Shadow Detection in Remote Sensing Applications](https://mlsanity.com/paper/2504.06920/) (2025)
- [SwinShadow: Shifted Window for Ambiguous Adjacent Shadow Detection](https://mlsanity.com/paper/2408.03521/) (2024)
- [ShadowHack: Hacking Shadows via Luminance-Color Divide and Conquer](https://mlsanity.com/paper/2412.02545/) (2024)
- [Towards Real Zero-Shot Camouflaged Object Segmentation without Camouflaged Annotations](https://mlsanity.com/paper/2410.16953/) (2024)
- [Prompt-Aware Controllable Shadow Removal](https://mlsanity.com/paper/2501.15043/) (2025)
- [VIP: Video Inpainting Pipeline for Real World Human Removal](https://mlsanity.com/paper/2504.03041/) (2025)
- [RenDetNet: Weakly-supervised Shadow Detection with Shadow Caster Verification](https://mlsanity.com/paper/2408.17143/) (2024)
- [DTTNet: Improving Video Shadow Detection via Dark-Aware Guidance and Tokenized Temporal Modeling](https://mlsanity.com/paper/2511.06925/) (2025)
- [Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoning](https://mlsanity.com/paper/2512.06179/) (2025)
- [Revisiting Shadow Detection from a Vision-Language Perspective](https://mlsanity.com/paper/2605.11771/) (2026)
- [After a Decade: Bringing Shadow Removal into the Real World with Agentic Training Data](https://mlsanity.com/paper/2609.38607/) (2026)

## Abstract (arXiv)

Existing shadow detection datasets often contain missing or mislabeled shadows, which can hinder the performance of deep learning models trained directly on such data. To address this issue, we propose SILT, the Shadow-aware Iterative Label Tuning framework, which explicitly considers noise in shadow labels and trains the deep model in a self-training manner. Specifically, we incorporate strong data augmentations with shadow counterfeiting to help the network better recognize non-shadow regions and alleviate overfitting. We also devise a simple yet effective label tuning strategy with global-local fusion and shadow-aware filtering to encourage the network to make significant refinements on the noisy labels. We evaluate the performance of SILT by relabeling the test set of the SBU dataset and conducting various experiments. Our results show that even a simple U-Net trained with SILT can outperform all state-of-the-art methods by a large margin. When trained on SBU / UCF / ISTD, our network can successfully reduce the Balanced Error Rate by 25.2% / 36.9% / 21.3% over the best state-of-the-art method.