IRDCLNet: Instance Segmentation of Ship Images Based on Interference Reduction and Dynamic Contour Learning in Foggy Scenes

Sun, Yuxin; Su, Li; Meng, Hao; Zhang, Zhi; Zhang, Wen; Yuan, Shouzheng

doi:10.1109/tcsvt.2022.3155182

Cited by 14 publications

(4 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address these challenges, determining the extent of forest fires on foggy days has become an important and challenging problem that needs to be solved. In previous research on defogging semantic segmentation, many methods have adopted a two-stage processing strategy, where defogging image extraction is followed by semantic segmentation [24,25]. However, this approach may result in information loss, as important semantic information may be lost during the defogging image extraction process.…”

Section: Discussionmentioning

confidence: 99%

“…On the other hand, there have been effective solutions developed for defogging segmentation of other objects. For instance, IRDCLNet provides a fog segmentation solution for ships that uses an interference reduction module and a dynamic contour learning module [24]. Another illustration is the work of Zhu et al, which enhances the defogging technique by using a dual attention mechanism and an SOS acceleration module [25].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Defogging Learning Based on an Improved DeepLabV3+ Model for Accurate Foggy Forest Fire Segmentation

Liu,

Chen,

Lin

et al. 2023

Forests

View full text Add to dashboard Cite

In recent years, the utilization of deep learning for forest fire detection has yielded favorable outcomes. Nevertheless, the accurate segmentation of forest fires in foggy surroundings with limited visibility remains a formidable obstacle. To overcome this challenge, a collaborative defogging learning framework, known as Defog DeepLabV3+, predicated on an enhanced DeepLabV3+ model is presented. Improved learning and precise flame segmentation are accomplished by merging the defogging features produced by the defogging branch in the input image. Furthermore, dual fusion attention residual feature attention (DARA) is proposed to enhance the extraction of flame-related features. The FFLAD dataset was developed given the scarcity of specifically tailored datasets for flame recognition in foggy environments. The experimental findings attest to the efficacy of our model, with a Mean Precision Accuracy (mPA) of 94.26%, a mean recall (mRecall) of 94.04%, and a mean intersection over union (mIoU) of 89.51%. These results demonstrate improvements of 2.99%, 3.89%, and 5.22% respectively. The findings reveal that the suggested model exhibits exceptional accuracy in foggy conditions, surpassing other existing models across all evaluation metrics.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Defogging Learning Based on an Improved DeepLabV3+ Model for Accurate Foggy Forest Fire Segmentation

Liu,

Chen,

Lin

et al. 2023

Forests

View full text Add to dashboard Cite

show abstract

“…Current studies [23], [25], [26] usually start from generating class activation maps [6] by training a classification network to build the seeds and then utilize refinement techniques [1], [2], for generating reliable pseudo masks, which are finally used to train the segmentation model [37], [44]. In this work, we concentrate on the image-level weakly supervised semantic segmentation, where only the images' class labels are given; we aim to enhance the quality of seeds and, thus, the segmentation results.…”

Section: Introductionmentioning

confidence: 99%

Contour-Aware Equipotential Learning for Semantic Segmentation

Yin

Min

Huo

et al. 2023

IEEE Trans. Multimedia

View full text Add to dashboard Cite

With increasing demands for high-quality semantic segmentation in the industry, hard-distinguishing semantic boundaries have posed a significant threat to existing solutions. Inspired by real-life experience, i.e., combining varied observations contributes to higher visual recognition confidence, we present the equipotential learning (EPL) method. This novel module transfers the predicted/ground-truth semantic labels to a self-defined potential domain to learn and infer decision boundaries along customized directions. The conversion to the potential domain is implemented via a lightweight differentiable anisotropic convolution without incurring any parameter overhead. Besides, the designed two loss functions, the point loss and the equipotential line loss implement anisotropic field regression and category-level contour learning, respectively, enhancing prediction consistencies in the inter/intra-class boundary areas. More importantly, EPL is agnostic to network architectures, and thus it can be plugged into most existing segmentation models. This paper is the first attempt to address the boundary segmentation problem with field regression and contour learning. Meaningful performance improvements on Pascal Voc 2012 and Cityscapes demonstrate that the proposed EPL module can benefit the offthe-shelf fully convolutional network models when recognizing semantic boundary areas. Besides, intensive comparisons and analysis show the favorable merits of EPL for distinguishing semantically-similar and irregular-shaped categories.

show abstract

“…clouds, then the subsequent task involves the discernment and classification of the cloud types to identify their specific categories. Pixel-level segmentation algorithms [2]- [4], bolstered by the advancement of deep learning technologies, have made rapid progress in the field of natural image processing. They are capable of dividing images into fine-grained pixel-level regions, thereby identifying and classifying various objects and textures within the images.…”

Section: Introductionmentioning

confidence: 99%

Context-Aware Attention Network for Image-Text Retrieval

Zhang

Lei

Zhang

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

186

View full text Add to dashboard Cite

Accurate cloud recognition and warning are crucial for various applications, including in-flight support, weather forecasting, and climate research. However, recent deep learning algorithms have predominantly focused on detecting cloud regions in satellite imagery, with insufficient attention to the specificity required for accurate cloud recognition. This limitation inspired us to develop the novel FY-4A-Himawari-8 (FYH) dataset, which includes nine distinct cloud categories and uses precise domain adaptation methods to align 70,419 image-label pairs in terms of projection, temporal resolution, and spatial resolution, thereby facilitating the training of supervised deep learning networks. Given the complexity and diversity of cloud formations, we have thoroughly analyzed the challenges inherent to cloud recognition tasks, examining the intricate characteristics and distribution of the data. To effectively address these challenges, we designed a Distribution-aware Interactive-Attention Network (DIAnet), which preserves pixel-level details through a high-resolution branch and a parallel multi-resolution crossbranch. We also integrated a distribution-aware loss (DAL) to mitigate the imbalance across cloud categories. An Interactive Attention Module (IAM) further enhances the robustness of feature extraction combined with spatial and channel information. Empirical evaluations on the FYH dataset demonstrate that our method outperforms other cloud recognition networks, achieving superior performance in terms of mean Intersection over Union (mIoU). The code for implementing DIAnet is available at https://github.com/icey-zhang/DIAnet.

show abstract

IRDCLNet: Instance Segmentation of Ship Images Based on Interference Reduction and Dynamic Contour Learning in Foggy Scenes

Cited by 14 publications

References 47 publications

Defogging Learning Based on an Improved DeepLabV3+ Model for Accurate Foggy Forest Fire Segmentation

Defogging Learning Based on an Improved DeepLabV3+ Model for Accurate Foggy Forest Fire Segmentation

Contour-Aware Equipotential Learning for Semantic Segmentation

Context-Aware Attention Network for Image-Text Retrieval

Contact Info

Product

Resources

About