Related papers: Mutual Learning for Domain Adaptation: Self-distillation Image Dehazing Network with Sample-cycle

Mutual Learning for Domain Adaptation: Self-distillation Image Dehazing Network with Sample-cycle

URL: http://arxiv.org/abs/2203.09430v1
Date: Thu, 17 Mar 2022 16:32:14 GMT
Title: Mutual Learning for Domain Adaptation: Self-distillation Image Dehazing Network with Sample-cycle
Authors: Tian Ye, Yun Liu, Yunchen Zhang, Sixiang Chen, Erkang Chen
Abstract summary: We propose a mutual learning dehazing framework for domain adaption. Specifically, we first devise two siamese networks: a teacher network in the synthetic domain and a student network in the real domain. We show that the framework outperforms state-of-the-art dehazing techniques in terms of subjective and objective evaluation.
Score: 7.452382358080454
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Deep learning-based methods have made significant achievements for image dehazing. However, most of existing dehazing networks are concentrated on training models using simulated hazy images, resulting in generalization performance degradation when applied on real-world hazy images because of domain shift. In this paper, we propose a mutual learning dehazing framework for domain adaption. Specifically, we first devise two siamese networks: a teacher network in the synthetic domain and a student network in the real domain, and then optimize them in a mutual learning manner by leveraging EMA and joint loss. Moreover, we design a sample-cycle strategy based on density augmentation (HDA) module to introduce pseudo real-world image pairs provided by the student network into training for further improving the generalization performance. Extensive experiments on both synthetic and real-world dataset demonstrate that the propose mutual learning framework outperforms state-of-the-art dehazing techniques in terms of subjective and objective evaluation.

Related papers

HazeCLIP: Towards Language Guided Real-World Image Dehazing [62.4454483961341]
Existing methods have achieved remarkable performance in single image dehazing, particularly on synthetic datasets. This paper introduces HazeCLIP, a language-guided adaptation framework designed to enhance the real-world performance of pre-trained dehazing networks.
arXiv Detail & Related papers (2024-07-18T17:18:25Z)
Teacher-Student Network for Real-World Face Super-Resolution with Progressive Embedding of Edge Information [2.280954956645056]
A real-world face super-resolution teacher-student model is proposed, which considers the domain gap between real and synthetic data. Our proposed approach surpasses state-of-the-art methods in obtaining high-quality face images for real-world FSR.
arXiv Detail & Related papers (2024-05-08T02:48:52Z)
Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems [80.62854148838359]
Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate. We use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data. Our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.
arXiv Detail & Related papers (2024-03-23T22:32:06Z)
Uni-Removal: A Semi-Supervised Framework for Simultaneously Addressing Multiple Degradations in Real-World Images [6.3351090376024155]
Uni-Removal is a twostage semi-supervised framework for addressing the removal of multiple degradations in real-world images. In the knowledge transfer stage, Uni-Removal leverages a supervised multi-teacher and student architecture. In the domain adaptation stage, unsupervised fine-tuning is performed by incorporating an adversarial discriminator on real-world images.
arXiv Detail & Related papers (2023-07-11T07:18:15Z)
Unsupervised Domain Transfer with Conditional Invertible Neural Networks [83.90291882730925]
We propose a domain transfer approach based on conditional invertible neural networks (cINNs) Our method inherently guarantees cycle consistency through its invertible architecture, and network training can efficiently be conducted with maximum likelihood. Our method enables the generation of realistic spectral data and outperforms the state of the art on two downstream classification tasks.
arXiv Detail & Related papers (2023-03-17T18:00:27Z)
Bridging Synthetic and Real Images: a Transferable and Multiple Consistency aided Fundus Image Enhancement Framework [61.74188977009786]
We propose an end-to-end optimized teacher-student framework to simultaneously conduct image enhancement and domain adaptation. We also propose a novel multi-stage multi-attention guided enhancement network (MAGE-Net) as the backbones of our teacher and student network.
arXiv Detail & Related papers (2023-02-23T06:16:15Z)
Domain Adaptation for Image Dehazing [72.15994735131835]
Most existing methods train a dehazing model on synthetic hazy images, which are less able to generalize well to real hazy images due to domain shift. We propose a domain adaptation paradigm, which consists of an image translation module and two image dehazing modules. Experimental results on both synthetic and real-world images demonstrate that our model performs favorably against the state-of-the-art dehazing algorithms.
arXiv Detail & Related papers (2020-05-10T13:54:56Z)
Two-shot Spatially-varying BRDF and Shape Estimation [89.29020624201708]
We propose a novel deep learning architecture with a stage-wise estimation of shape and SVBRDF. We create a large-scale synthetic training dataset with domain-randomized geometry and realistic materials. Experiments on both synthetic and real-world datasets show that our network trained on a synthetic dataset can generalize well to real-world images.
arXiv Detail & Related papers (2020-04-01T12:56:13Z)

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