# Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation

arXiv: https://arxiv.org/abs/2211.13409 · HTML: https://mlsanity.com/paper/2211.13409/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 24 Nov 2022.

## Builds on (most cited first, 20 of 20)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing](https://mlsanity.com/paper/1908.03245/) (2019)
- [Learning Depth-Guided Convolutions for Monocular 3D Object Detection](https://mlsanity.com/paper/1912.04799/) (2019)
- [Densely Connected Pyramid Dehazing Network](https://mlsanity.com/paper/1803.08396/) (2018)
- [MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2103.04224/) (2021)
- [DADA: Depth-aware Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1904.01886/) (2019)
- [Category Contrast for Unsupervised Domain Adaptation in Visual Tasks](https://mlsanity.com/paper/2106.02885/) (2021)
- [Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection](https://mlsanity.com/paper/2103.00236/) (2021)
- [SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses](https://mlsanity.com/paper/1911.02559/) (2019)
- [Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2105.07830/) (2021)
- [Self-Adversarial Disentangling for Specific Domain Adaptation](https://mlsanity.com/paper/2108.03553/) (2021)
- [Multi-Granularity Alignment Domain Adaptation for Object Detection](https://mlsanity.com/paper/2203.16897/) (2022)

## Built on by (most cited first, 2 of 2)

- [Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation](https://mlsanity.com/paper/2504.03193/) (2025)
- [MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection](https://mlsanity.com/paper/2407.16448/) (2024)

## Abstract (arXiv)

Most existing domain adaptation (DA) methods align the features based on the domain feature distributions and ignore aspects related to fog, background and target objects, rendering suboptimal performance. In our DA framework, we retain the depth and background information during the domain feature alignment. A consistency loss between the generated depth and fog transmission map is introduced to strengthen the retention of the depth information in the aligned features. To address false object features potentially generated during the DA process, we propose an encoder-decoder framework to reconstruct the fog-free background image. This reconstruction loss also reinforces the encoder, i.e., our DA backbone, to minimize false object features.Moreover, we involve our target data in training both our DA module and our detection module in a semi-supervised manner, so that our detection module is also exposed to the unlabeled target data, the type of data used in the testing stage. Using these ideas, our method significantly outperforms the state-of-the-art method (47.6 mAP against the 44.3 mAP on the Foggy Cityscapes dataset), and obtains the best performance on multiple real-image public datasets. Code is available at: https://github.com/VIML-CVDL/Object-Detection-in-Foggy-Scenes