# Test-Time Intensity Consistency Adaptation for Shadow Detection

arXiv: https://arxiv.org/abs/2410.07695 · HTML: https://mlsanity.com/paper/2410.07695/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 79 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal](https://mlsanity.com/paper/1712.02478/) (2017)
- [Explicit Visual Prompting for Low-Level Structure Segmentations](https://mlsanity.com/paper/2303.10883/) (2023)
- [The Fast Bilateral Solver](https://mlsanity.com/paper/1511.03296/) (2015)
- [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)
- [High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net](https://mlsanity.com/paper/2308.14221/) (2023)
- [CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying](https://mlsanity.com/paper/2303.08524/) (2023)
- [Depth-aware Test-Time Training for Zero-shot Video Object Segmentation](https://mlsanity.com/paper/2403.04258/) (2024)
- [DOPRA: Decoding Over-accumulation Penalization and Re-allocation in Specific Weighting Layer](https://mlsanity.com/paper/2407.15130/) (2024)
- [TEA: Test-time Energy Adaptation](https://mlsanity.com/paper/2311.14402/) (2023)
- [A Large-scale Film Style Dataset for Learning Multi-frequency Driven Film Enhancement](https://mlsanity.com/paper/2301.08880/) (2023)
- [Brain Diffuser: An End-to-End Brain Image to Brain Network Pipeline](https://mlsanity.com/paper/2303.06410/) (2023)
- [Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2310.09760/) (2023)
- [SiENet: Siamese Expansion Network for Image Extrapolation](https://mlsanity.com/paper/2007.03851/) (2020)
- [Dual-Hybrid Attention Network for Specular Highlight Removal](https://mlsanity.com/paper/2407.12255/) (2024)
- [Explicit Visual Prompting for Universal Foreground Segmentations](https://mlsanity.com/paper/2305.18476/) (2023)
- [Devignet: High-Resolution Vignetting Removal via a Dual Aggregated Fusion Transformer With Adaptive Channel Expansion](https://mlsanity.com/paper/2308.13739/) (2023)
- [ShaDocNet: Learning Spatial-Aware Tokens in Transformer for Document Shadow Removal](https://mlsanity.com/paper/2211.16675/) (2022)
- [MFDNet: Multi-Frequency Deflare Network for Efficient Nighttime Flare Removal](https://mlsanity.com/paper/2406.18079/) (2024)

## Built on by (most cited first, 11 of 11)

- [Underwater Image Restoration via Polymorphic Large Kernel CNNs](https://mlsanity.com/paper/2412.18459/) (2024)
- [High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer](https://mlsanity.com/paper/2410.22922/) (2024)
- [LensNet: An End-to-End Learning Framework for Empirical Point Spread Function Modeling and Lensless Imaging Reconstruction](https://mlsanity.com/paper/2505.01755/) (2025)
- [IMAN: An Adaptive Network for Robust NPC Mortality Prediction with Missing Modalities](https://mlsanity.com/paper/2410.18551/) (2024)
- [DLEN: Dual Branch of Transformer for Low-Light Image Enhancement in Dual Domains](https://mlsanity.com/paper/2501.12235/) (2025)
- [MAC-Lookup: Multi-Axis Conditional Lookup Model for Underwater Image Enhancement](https://mlsanity.com/paper/2507.02270/) (2025)
- [TAGE: Trustworthy Attribute Group Editing for Stable Few-shot Image Generation](https://mlsanity.com/paper/2410.17855/) (2024)
- [SFormer: SNR-guided Transformer for Underwater Image Enhancement from the Frequency Domain](https://mlsanity.com/paper/2508.18664/) (2025)
- [A Comprehensive Analysis of Churn Prediction in Telecommunications Using Machine Learning](https://mlsanity.com/paper/2509.22654/) (2025)
- [Forestpest-YOLO: A High-Performance Detection Framework for Small Forestry Pests](https://mlsanity.com/paper/2510.00547/) (2025)
- [DTEA: Dynamic Topology Weaving and Instability-Driven Entropic Attenuation for Medical Image Segmentation](https://mlsanity.com/paper/2510.11259/) (2025)

## Abstract (arXiv)

Shadow detection is crucial for accurate scene understanding in computer vision, yet it is challenged by the diverse appearances of shadows caused by variations in illumination, object geometry, and scene context. Deep learning models often struggle to generalize to real-world images due to the limited size and diversity of training datasets. To address this, we introduce TICA, a novel framework that leverages light-intensity information during test-time adaptation to enhance shadow detection accuracy. TICA exploits the inherent inconsistencies in light intensity across shadow regions to guide the model toward a more consistent prediction. A basic encoder-decoder model is initially trained on a labeled dataset for shadow detection. Then, during the testing phase, the network is adjusted for each test sample by enforcing consistent intensity predictions between two augmented input image versions. This consistency training specifically targets both foreground and background intersection regions to identify shadow regions within images accurately for robust adaptation. Extensive evaluations on the ISTD and SBU shadow detection datasets reveal that TICA significantly demonstrates that TICA outperforms existing state-of-the-art methods, achieving superior results in balanced error rate (BER).