# Zero-Shot Day-Night Domain Adaptation with a Physics Prior

arXiv: https://arxiv.org/abs/2108.05137 · HTML: https://mlsanity.com/paper/2108.05137/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 84 references that are in the map.
- First posted on arXiv 11 Aug 2021.

## Builds on (most cited first, 30 of 49)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation](https://mlsanity.com/paper/1611.06612/) (2016)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://mlsanity.com/paper/1612.02649/) (2016)
- [Learning with Average Precision: Training Image Retrieval with a Listwise Loss](https://mlsanity.com/paper/1906.07589/) (2019)
- [Label-Embedding for Image Classification](https://mlsanity.com/paper/1503.08677/) (2015)
- [Particular object retrieval with integral max-pooling of CNN activations](https://mlsanity.com/paper/1511.05879/) (2015)
- [Getting to Know Low-light Images with The Exclusively Dark Dataset](https://mlsanity.com/paper/1805.11227/) (2018)
- [Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning](https://mlsanity.com/paper/1904.05050/) (2019)
- [On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location](https://mlsanity.com/paper/2003.07064/) (2020)
- [Zero-Shot Learning by Convex Combination of Semantic Embeddings](https://mlsanity.com/paper/1312.5650/) (2013)
- [Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime](https://mlsanity.com/paper/1810.02575/) (2018)
- [VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change](https://mlsanity.com/paper/2005.08135/) (2020)
- [Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation](https://mlsanity.com/paper/2005.14553/) (2020)
- [On the Performance of ConvNet Features for Place Recognition](https://mlsanity.com/paper/1501.04158/) (2015)

## Built on by (most cited first, 30 of 47)

- [PODA: Prompt-driven Zero-shot Domain Adaptation](https://mlsanity.com/paper/2212.03241/) (2022)
- [2PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2303.13853/) (2023)
- [A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects](https://mlsanity.com/paper/2305.07348/) (2023)
- [Unified Language-driven Zero-shot Domain Adaptation](https://mlsanity.com/paper/2404.07155/) (2024)
- [A Simple Recipe for Language-guided Domain Generalized Segmentation](https://mlsanity.com/paper/2311.17922/) (2023)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Day-to-Night Image Synthesis for Training Nighttime Neural ISPs](https://mlsanity.com/paper/2206.02715/) (2022)
- [Prior Knowledge Guided Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.08877/) (2022)
- [GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditions](https://mlsanity.com/paper/2209.14922/) (2022)
- [Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey](https://mlsanity.com/paper/2112.03241/) (2021)
- [Diversifying Spatial-Temporal Perception for Video Domain Generalization](https://mlsanity.com/paper/2310.17942/) (2023)
- [Deep vanishing point detection: Geometric priors make dataset variations vanish](https://mlsanity.com/paper/2203.08586/) (2022)
- [Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2312.01220/) (2023)
- [Learning Physics From Video: Unsupervised Physical Parameter Estimation for Continuous Dynamical Systems](https://mlsanity.com/paper/2410.01376/) (2024)
- [Knowledge-augmented Deep Learning and Its Applications: A Survey](https://mlsanity.com/paper/2212.00017/) (2022)
- [Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2307.08779/) (2023)
- [Fearless Luminance Adaptation: A Macro-Micro-Hierarchical Transformer for Exposure Correction](https://mlsanity.com/paper/2309.00872/) (2023)
- [Human-Centric Transformer for Domain Adaptive Action Recognition](https://mlsanity.com/paper/2407.10860/) (2024)
- [Color Equivariant Convolutional Networks](https://mlsanity.com/paper/2310.19368/) (2023)
- [Practical exposure correction via compensation](https://mlsanity.com/paper/2212.14245/) (2022)
- [Instance-level Few-shot Learning with Class Hierarchy Mining](https://mlsanity.com/paper/2304.07459/) (2023)
- [ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfer](https://mlsanity.com/paper/2403.13652/) (2024)
- [Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design](https://mlsanity.com/paper/2504.14075/) (2025)
- [Holistic Dynamic Frequency Transformer for Image Fusion and Exposure Correction](https://mlsanity.com/paper/2309.01183/) (2023)
- [UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement](https://mlsanity.com/paper/2507.00721/) (2025)
- [Ensemble-Based Event Camera Place Recognition Under Varying Illumination](https://mlsanity.com/paper/2509.01968/) (2025)
- [Priors in Deep Image Restoration and Enhancement: A Survey](https://mlsanity.com/paper/2206.02070/) (2022)
- [Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning](https://mlsanity.com/paper/2309.16351/) (2023)
- [From Enhancement to Understanding: Build a Generalized Bridge for Low-light Vision via Semantically Consistent Unsupervised Fine-tuning](https://mlsanity.com/paper/2507.08380/) (2025)
- [Interpretable Distribution Shift Detection using Optimal Transport](https://mlsanity.com/paper/2208.02896/) (2022)

## Abstract (arXiv)

We explore the zero-shot setting for day-night domain adaptation. The traditional domain adaptation setting is to train on one domain and adapt to the target domain by exploiting unlabeled data samples from the test set. As gathering relevant test data is expensive and sometimes even impossible, we remove any reliance on test data imagery and instead exploit a visual inductive prior derived from physics-based reflection models for domain adaptation. We cast a number of color invariant edge detectors as trainable layers in a convolutional neural network and evaluate their robustness to illumination changes. We show that the color invariant layer reduces the day-night distribution shift in feature map activations throughout the network. We demonstrate improved performance for zero-shot day to night domain adaptation on both synthetic as well as natural datasets in various tasks, including classification, segmentation and place recognition.