# UniDet-D: A Unified Dynamic Spectral Attention Model for Object Detection under Adverse Weathers

arXiv: https://arxiv.org/abs/2506.12324 · HTML: https://mlsanity.com/paper/2506.12324/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 56 references that are in the map.
- First posted on arXiv 14 Jun 2025.

## Builds on (most cited first, 30 of 33)

- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [Libra R-CNN: Towards Balanced Learning for Object Detection](https://mlsanity.com/paper/1904.02701/) (2019)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain](https://mlsanity.com/paper/2401.16822/) (2024)
- [FcaNet: Frequency Channel Attention Networks](https://mlsanity.com/paper/2012.11879/) (2020)
- [FSDR: Frequency Space Domain Randomization for Domain Generalization](https://mlsanity.com/paper/2103.02370/) (2021)
- [Getting to Know Low-light Images with The Exclusively Dark Dataset](https://mlsanity.com/paper/1805.11227/) (2018)
- [Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training](https://mlsanity.com/paper/2004.06002/) (2020)
- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions](https://mlsanity.com/paper/2112.08088/) (2021)
- [Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey](https://mlsanity.com/paper/2112.08936/) (2021)
- [You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction](https://mlsanity.com/paper/2205.14871/) (2022)
- [AdaMixer: A Fast-Converging Query-Based Object Detector](https://mlsanity.com/paper/2203.16507/) (2022)
- [Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection](https://mlsanity.com/paper/2205.03346/) (2022)
- [3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds](https://mlsanity.com/paper/2304.00690/) (2023)
- [Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather](https://mlsanity.com/paper/2210.15176/) (2022)
- [Spectral Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2106.06112/) (2021)
- [2PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2303.13853/) (2023)
- [EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing](https://mlsanity.com/paper/2407.13596/) (2024)
- [GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditions](https://mlsanity.com/paper/2209.14922/) (2022)
- [Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filters](https://mlsanity.com/paper/2207.01331/) (2022)
- [TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learning](https://mlsanity.com/paper/2209.01373/) (2022)

## Abstract (arXiv)

Real-world object detection is a challenging task where the captured images/videos often suffer from complex degradations due to various adverse weather conditions such as rain, fog, snow, low-light, etc. Despite extensive prior efforts, most existing methods are designed for one specific type of adverse weather with constraints of poor generalization, under-utilization of visual features while handling various image degradations. Leveraging a theoretical analysis on how critical visual details are lost in adverse-weather images, we design UniDet-D, a unified framework that tackles the challenge of object detection under various adverse weather conditions, and achieves object detection and image restoration within a single network. Specifically, the proposed UniDet-D incorporates a dynamic spectral attention mechanism that adaptively emphasizes informative spectral components while suppressing irrelevant ones, enabling more robust and discriminative feature representation across various degradation types. Extensive experiments show that UniDet-D achieves superior detection accuracy across different types of adverse-weather degradation. Furthermore, UniDet-D demonstrates superior generalization towards unseen adverse weather conditions such as sandstorms and rain-fog mixtures, highlighting its great potential for real-world deployment.