# Scaling Up Single Image Dehazing Algorithm by Cross-Data Vision Alignment for Richer Representation Learning and Beyond

arXiv: https://arxiv.org/abs/2407.14823 · HTML: https://mlsanity.com/paper/2407.14823/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 42 references that are in the map.
- First posted on arXiv 20 Jul 2024.

## Builds on (most cited first, 18 of 18)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [DehazeNet: An End-to-End System for Single Image Haze Removal](https://mlsanity.com/paper/1601.07661/) (2016)
- [Whitening for Self-Supervised Representation Learning](https://mlsanity.com/paper/2007.06346/) (2020)
- [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022)
- [Unsupervised Learning of Dense Visual Representations](https://mlsanity.com/paper/2011.05499/) (2020)
- [SegSort: Segmentation by Discriminative Sorting of Segments](https://mlsanity.com/paper/1910.06962/) (2019)
- [DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention](https://mlsanity.com/paper/2301.04805/) (2023)
- [ReSSL: Relational Self-Supervised Learning with Weak Augmentation](https://mlsanity.com/paper/2107.09282/) (2021)
- [Self-Supervised Visual Representation Learning from Hierarchical Grouping](https://mlsanity.com/paper/2012.03044/) (2020)
- [UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning](https://mlsanity.com/paper/2205.01871/) (2022)
- [Exploring Set Similarity for Dense Self-supervised Representation Learning](https://mlsanity.com/paper/2107.08712/) (2021)
- [MixDehazeNet : Mix Structure Block For Image Dehazing Network](https://mlsanity.com/paper/2305.17654/) (2023)
- [SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised Learning for Robust Infrared Small Target Detection](https://mlsanity.com/paper/2403.05416/) (2024)
- [A Data-Centric Solution to NonHomogeneous Dehazing via Vision Transformer](https://mlsanity.com/paper/2304.07874/) (2023)
- [Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior](https://mlsanity.com/paper/2406.00632/) (2024)

## Built on by (most cited first, 3 of 3)

- [ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration](https://mlsanity.com/paper/2601.02763/) (2026)
- [Thresholded Cross-Attention for Reliable Intensity-Chromaticity Fusion in Low-Light Image Enhancement](https://mlsanity.com/paper/2607.13925/) (2026)
- [PP-Net: A Hybrid Physical-Prior Neural Network for Scattered Light Removal in Biomedical Images on Embedded Devices](https://mlsanity.com/paper/2609.26474/) (2026)

## Abstract (arXiv)

In recent years, deep neural networks tasks have increasingly relied on high-quality image inputs. With the development of high-resolution representation learning, the task of image dehazing has received significant attention. Previously, many methods collect diverse image data for large-scale training to boost the performance on a target scene. Ignoring the domain gap between different data, former de-hazing methods simply adopt multiple datasets for explicit large-scale training, which often makes the methods themselves be violated. To address this problem, we propose a novel method of cross-data vision alignment for richer representation learning to improve the existing dehazing methodology. Specifically, we call for the internal- and external knowledge should be further adapted with a self-supervised manner to fill up the domain gap. By using cross-data external alignment, the datasets inherit samples from different domains that are firmly aligned, making the model learn more robust and generalizable features. By using the internal augmentation method, the model can fully exploit local information within the images, and then obtaining more image details. To demonstrate the effectiveness of our proposed method, we conduct training on the Natural Image Dataset (NID). Experimental results show that our method clearly resolves the domain gap in different dehazing datasets and presents a new pipeline for large-scale training in the dehazing task. Our approach significantly outperforms other advanced methods in dehazing and produces dehazed images that are closest to real haze-free images.