DAMix: Density-Aware Data Augmentation for Unsupervised Domain Adaptation on Single Image Dehazing

• URL: http://arxiv.org/abs/2109.12544v1
• Date: Sun, 26 Sep 2021 09:45:59 GMT
• Title: DAMix: Density-Aware Data Augmentation for Unsupervised Domain Adaptation on Single Image Dehazing
• Authors: Chia-Ming Chang, Chang-Sung Sung, Tsung-Nan Lin
• Abstract summary: We propose a density-aware data augmentation method (DAMix) that generates synthetic hazy samples according to the haze density level of the target domain. DAMix ensures that the model learns from examples featuring diverse haze densities. We develop a dual-branch dehazing network involving two branches that can adaptively remove haze according to the haze density of the region.
• Score: 2.2678980997015534
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning-based methods have achieved great success on single image dehazing in recent years. However, these methods are often subject to performance degradation when domain shifts are confronted. Specifically, haze density gaps exist among the existing datasets, often resulting in poor performance when these methods are tested across datasets. To address this issue, we propose a density-aware data augmentation method (DAMix) that generates synthetic hazy samples according to the haze density level of the target domain. These samples are generated by combining a hazy image with its corresponding ground truth by a combination ratio sampled from a density-aware distribution. They not only comply with the atmospheric scattering model but also bridge the haze density gap between the source and target domains. DAMix ensures that the model learns from examples featuring diverse haze densities. To better utilize the various hazy samples generated by DAMix, we develop a dual-branch dehazing network involving two branches that can adaptively remove haze according to the haze density of the region. In addition, the dual-branch design enlarges the learning capacity of the entire network; hence, our network can fully utilize the DAMix-ed samples. We evaluate the effectiveness of DAMix by applying it to the existing open-source dehazing methods. The experimental results demonstrate that all methods show significant improvements after DAMix is applied. Furthermore, by combining DAMix with our model, we can achieve state-of-the-art (SOTA) performance in terms of domain adaptation.

Related papers

• Towards Effective Data-Free Knowledge Distillation via Diverse Diffusion Augmentation [20.556083321381514]
  Data-free knowledge distillation (DFKD) has emerged as a pivotal technique in the domain of model compression. This paper introduces an innovative approach to DFKD through diverse diffusion augmentation (DDA) Comprehensive experiments conducted on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets showcase the superior performance of our method.
  arXiv  Detail & Related papers  (2024-10-23T07:01:16Z)
• LMHaze: Intensity-aware Image Dehazing with a Large-scale Multi-intensity Real Haze Dataset [14.141433473509826]
  We present LMHaze, a large-scale, high-quality real-world dataset. LMHaze comprises paired hazy and haze-free images captured in diverse indoor and outdoor environments. To better handle images with different haze intensities, we propose a mixture-of-experts model based on Mamba.
  arXiv  Detail & Related papers  (2024-10-21T15:20:02Z)
• Mitigating Embedding Collapse in Diffusion Models for Categorical Data [52.90687881724333]
  We introduce CATDM, a continuous diffusion framework within the embedding space that stabilizes training. Experiments on benchmarks show that CATDM mitigates embedding collapse, yielding superior results on FFHQ, LSUN Churches, and LSUN Bedrooms.
  arXiv  Detail & Related papers  (2024-10-18T09:12:33Z)
• Gaussian Mixture based Evidential Learning for Stereo Matching [20.143918649298424]
  Our framework posits that individual image data adheres to a mixture-of-Gaussian distribution in stereo matching. Our approach achieved new state-of-the-art results on both the in-domain validated data and the cross-domain datasets.
  arXiv  Detail & Related papers  (2024-08-05T19:23:45Z)
• DreamDA: Generative Data Augmentation with Diffusion Models [68.22440150419003]
  This paper proposes a new classification-oriented framework DreamDA. DreamDA generates diverse samples that adhere to the original data distribution by considering training images in the original data as seeds. In addition, since the labels of the generated data may not align with the labels of their corresponding seed images, we introduce a self-training paradigm for generating pseudo labels.
  arXiv  Detail & Related papers  (2024-03-19T15:04:35Z)
• A Novel Approach to Industrial Defect Generation through Blended Latent Diffusion Model with Online Adaptation [10.422501665725902]
  This paper introduces a novel algorithm designed to augment defective samples, thereby enhancing industrial Anomaly Detection (AD) performance. Specifically, on the widely recognized MVTec AD dataset, the proposed method elevates the state-of-the-art (SOTA) performance of AD with augmented data by 1.5%, 1.9%, and 3.1% for AD metrics AP, IAP, and IAP90, respectively.
  arXiv  Detail & Related papers  (2024-02-29T16:33:12Z)
• Denoising Diffusion Bridge Models [54.87947768074036]
  Diffusion models are powerful generative models that map noise to data using processes. For many applications such as image editing, the model input comes from a distribution that is not random noise. In our work, we propose Denoising Diffusion Bridge Models (DDBMs)
  arXiv  Detail & Related papers  (2023-09-29T03:24:24Z)
• Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
  Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance. We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-22T12:18:20Z)
• ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Data [93.06336507035486]
  Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available. We present ScoreMix, a novel and scalable data augmentation approach for various image synthesis tasks.
  arXiv  Detail & Related papers  (2022-10-27T02:55:15Z)
• CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation [62.259239847977014]
  We propose a new approach of sample mixing for point cloud UDA, namely Compositional Semantic Mix (CoSMix) CoSMix consists of a two-branch symmetric network that can process labelled synthetic data (source) and real-world unlabelled point clouds (target) concurrently. We evaluate CoSMix on two large-scale datasets, showing that it outperforms state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2022-07-20T09:33:42Z)
• Perceiving and Modeling Density is All You Need for Image Dehazing [10.864016211811025]
  In the real world, the degradation of images taken under haze can be quite complex. Recent methods adopt deep neural networks to recover clean scenes from hazy images directly. We propose to solve the problem of modeling real-world haze degradation by perceiving and modeling density for uneven haze distribution.
  arXiv  Detail & Related papers  (2021-11-18T14:47:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.