Rethinking Performance Gains in Image Dehazing Networks

• URL: http://arxiv.org/abs/2209.11448v1
• Date: Fri, 23 Sep 2022 07:14:48 GMT
• Title: Rethinking Performance Gains in Image Dehazing Networks
• Authors: Yuda Song, Yang Zhou, Hui Qian, Xin Du
• Abstract summary: We make minimal modifications to popular U-Net to obtain a compact dehazing network. Specifically, we swap out the convolutional blocks in U-Net for residual blocks with the gating mechanism. With a significantly reduced overhead, gUNet is superior to state-of-the-art methods on multiple image dehazing datasets.
• Score: 25.371802581339576
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image dehazing is an active topic in low-level vision, and many image dehazing networks have been proposed with the rapid development of deep learning. Although these networks' pipelines work fine, the key mechanism to improving image dehazing performance remains unclear. For this reason, we do not target to propose a dehazing network with fancy modules; rather, we make minimal modifications to popular U-Net to obtain a compact dehazing network. Specifically, we swap out the convolutional blocks in U-Net for residual blocks with the gating mechanism, fuse the feature maps of main paths and skip connections using the selective kernel, and call the resulting U-Net variant gUNet. As a result, with a significantly reduced overhead, gUNet is superior to state-of-the-art methods on multiple image dehazing datasets. Finally, we verify these key designs to the performance gain of image dehazing networks through extensive ablation studies.

Related papers

• DRACO-DehazeNet: An Efficient Image Dehazing Network Combining Detail Recovery and a Novel Contrastive Learning Paradigm [3.649619954898362]
  Detail Recovery And Contrastive DehazeNet is a detailed image recovery network that tailors enhancements to specific dehazed scene contexts. A major innovation is its ability to train effectively with limited data, achieved through a novel quadruplet loss-based contrastive dehazing paradigm.
  arXiv  Detail & Related papers  (2024-10-18T16:48:31Z)
• GAMA-IR: Global Additive Multidimensional Averaging for Fast Image Restoration [22.53813258871828]
  We introduce an image restoration network that is both fast and yields excellent image quality. The network is designed to minimize the latency and memory consumption when executed on a standard GPU. We exceed the state-of-the-art result on real-world SIDD denoising by 0.11dB, while being 2 to 10 times faster.
  arXiv  Detail & Related papers  (2024-03-31T21:43:08Z)
• RDRN: Recursively Defined Residual Network for Image Super-Resolution [58.64907136562178]
  Deep convolutional neural networks (CNNs) have obtained remarkable performance in single image super-resolution. We propose a novel network architecture which utilizes attention blocks efficiently.
  arXiv  Detail & Related papers  (2022-11-17T11:06:29Z)
• Low-light Enhancement Method Based on Attention Map Net [1.2158275183241178]
  Low-light image enhancement is a crucial preprocessing task for some complex vision tasks. Target detection, image segmentation, and image recognition outcomes are all directly impacted by the impact of image enhancement. We suggest an improved network called BrightenNet that uses U-Net as its primary structure and incorporates a number of different attention mechanisms as a solution.
  arXiv  Detail & Related papers  (2022-08-19T13:18:35Z)
• Online-updated High-order Collaborative Networks for Single Image Deraining [51.22694467126883]
  Single image deraining is an important task for some downstream artificial intelligence applications such as video surveillance and self-driving systems. We propose a high-order collaborative network with multi-scale compact constraints and a bidirectional scale-content similarity mining module. Our proposed method performs favorably against eleven state-of-the-art methods on five public synthetic and one real-world dataset.
  arXiv  Detail & Related papers  (2022-02-14T09:09:08Z)
• Contrastive Learning for Compact Single Image Dehazing [41.83007400559068]
  We propose a novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples. CR ensures that the restored image is pulled to closer to the clear image and pushed to far away from the hazy image in the representation space. Considering trade-off between performance and memory storage, we develop a compact dehazing network based on autoencoder-like framework.
  arXiv  Detail & Related papers  (2021-04-19T14:56:21Z)
• AttendNets: Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers [81.17461895644003]
  We introduce AttendNets, low-precision, highly compact deep neural networks tailored for on-device image recognition. AttendNets possess deep self-attention architectures based on visual attention condensers. Results show AttendNets have significantly lower architectural and computational complexity when compared to several deep neural networks.
  arXiv  Detail & Related papers  (2020-09-30T01:53:17Z)
• Feature Flow: In-network Feature Flow Estimation for Video Object Detection [56.80974623192569]
  Optical flow is widely used in computer vision tasks to provide pixel-level motion information. A common approach is to:forward optical flow to a neural network and fine-tune this network on the task dataset. We propose a novel network (IFF-Net) with an textbfIn-network textbfFeature textbfFlow estimation module for video object detection.
  arXiv  Detail & Related papers  (2020-09-21T07:55:50Z)
• AdderSR: Towards Energy Efficient Image Super-Resolution [127.61437479490047]
  This paper studies the single image super-resolution problem using adder neural networks (AdderNet) Compared with convolutional neural networks, AdderNet utilizing additions to calculate the output features thus avoid massive energy consumptions of conventional multiplications.
  arXiv  Detail & Related papers  (2020-09-18T15:29:13Z)
• Designing and Training of A Dual CNN for Image Denoising [117.54244339673316]
  We propose a Dual denoising Network (DudeNet) to recover a clean image. DudeNet consists of four modules: a feature extraction block, an enhancement block, a compression block, and a reconstruction block.
  arXiv  Detail & Related papers  (2020-07-08T08:16:24Z)
• Image Restoration Using Deep Regulated Convolutional Networks [2.608905180175928]
  We propose the Deep Regulated Convolutional Network (RC-Net), a deep network composed of regulated sub-network blocks cascaded by skip-connections. RC-Nets have several compelling advantages: they embrace diversified features through large-small filter combinations, alleviate the hazy boundary and blurred details in image denoising and super-resolution problems. Our proposed RC-Nets outperform state-of-the-art approaches with significant performance gains in various image restoration tasks while demonstrating promising generalization ability.
  arXiv  Detail & Related papers  (2019-10-19T22:30:23Z)

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.