# Does Haze Removal Help CNN-based Image Classification?

arXiv: https://arxiv.org/abs/1810.05716 · HTML: https://mlsanity.com/paper/1810.05716/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2018.

## Built on by (most cited first, 20 of 20)

- [Lightweight Adaptive Feature De-drifting for Compressed Image Classification](https://mlsanity.com/paper/2401.01724/) (2024)
- [UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior](https://mlsanity.com/paper/2501.13134/) (2025)
- [FIFO: Learning Fog-invariant Features for Foggy Scene Segmentation](https://mlsanity.com/paper/2204.01587/) (2022)
- [Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding](https://mlsanity.com/paper/2112.00484/) (2021)
- [Task-driven Image Fusion with Learnable Fusion Loss](https://mlsanity.com/paper/2412.03240/) (2024)
- [A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning](https://mlsanity.com/paper/2106.03323/) (2021)
- [SAPNet: Segmentation-Aware Progressive Network for Perceptual Contrastive Deraining](https://mlsanity.com/paper/2111.08892/) (2021)
- [Is Underwater Image Enhancement All Object Detectors Need?](https://mlsanity.com/paper/2311.18814/) (2023)
- [Exploiting Diffusion Prior for Task-driven Image Restoration](https://mlsanity.com/paper/2507.22459/) (2025)
- [FogAdapt: Self-Supervised Domain Adaptation for Semantic Segmentation of Foggy Images](https://mlsanity.com/paper/2201.02588/) (2022)
- [Deep Unfolding Multi-modal Image Fusion Network via Attribution Analysis](https://mlsanity.com/paper/2502.01467/) (2025)
- [Task-Driven Deep Image Enhancement Network for Autonomous Driving in Bad Weather](https://mlsanity.com/paper/2110.07206/) (2021)
- [Boosting Visual Recognition in Real-world Degradations via Unsupervised Feature Enhancement Module with Deep Channel Prior](https://mlsanity.com/paper/2404.01703/) (2024)
- [Dynamic Test-Time Augmentation via Differentiable Functions](https://mlsanity.com/paper/2212.04681/) (2022)
- [Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution](https://mlsanity.com/paper/2606.28971/) (2026)
- [Unsupervised Variational Translator for Bridging Image Restoration and High-Level Vision Tasks](https://mlsanity.com/paper/2408.08149/) (2024)
- [Bridging Scales in Map Generation: A scale-aware cascaded generative mapping framework for seamless and consistent multi-scale cartographic representation](https://mlsanity.com/paper/2502.04991/) (2025)
- [TaskTok: Delving into Task Tokens for Task-driven Image Restoration](https://mlsanity.com/paper/2606.26615/) (2026)
- [DA-RAW: Domain Adaptive Object Detection for Real-World Adverse Weather Conditions](https://mlsanity.com/paper/2309.08152/) (2023)
- [Noise-Free One-Step LoRA for Task-Driven Image Restoration with Diffusion Priors](https://mlsanity.com/paper/2607.25390/) (2026)

## Abstract (arXiv)

Hazy images are common in real scenarios and many dehazing methods have been developed to automatically remove the haze from images. Typically, the goal of image dehazing is to produce clearer images from which human vision can better identify the object and structural details present in the images. When the ground-truth haze-free image is available for a hazy image, quantitative evaluation of image dehazing is usually based on objective metrics, such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM). However, in many applications, large-scale images are collected not for visual examination by human. Instead, they are used for many high-level vision tasks, such as automatic classification, recognition and categorization. One fundamental problem here is whether various dehazing methods can produce clearer images that can help improve the performance of the high-level tasks. In this paper, we empirically study this problem in the important task of image classification by using both synthetic and real hazy image datasets. From the experimental results, we find that the existing image-dehazing methods cannot improve much the image-classification performance and sometimes even reduce the image-classification performance.