Article
Geochemistry & Geophysics
Koushikey Chhapariya, Krishna Mohan Buddhiraju, Anil Kumar
Summary: This study proposes a convolutional neural network (CNN) based method for salient object detection in hyperspectral images. The method utilizes both spatial and spectral information, incorporating an extended morphological profile (EMP) and achieving better performance by combining information from nearby pixels and high-level features.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Qing Zhang, Rui Zhao, Liqian Zhang
Summary: Due to the rapid development of deep learning, the salient object detection has made significant progress, but the problem of constructing a powerful saliency detection network to generate saliency maps that highlight salient objects and suppress background noise effectively is still a challenging issue. In this paper, a novel trifurcated cascaded refinement network (TCRNet) is proposed to explore multi-level feature fusion and global information representation. The proposed network performs favorably against 20 state-of-the-art salient object detection methods on five benchmark datasets, demonstrating its effectiveness and superiority.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Wujie Zhou, Junwei Wu, Jingsheng Lei, Jenq-Neng Hwang, Lu Yu
Summary: The article introduces a novel Deep Convolutional Residual Autoencoder (DCRA) for salient object detection in stereoscopic 3D images, utilizing residual modules and feature map fusion modules to explore complex relationships and exploit complementarity between RGB and depth information. By optimizing the DCRA parameters through supervised learning with supervision pyramids and multiscale layers, superior performance to comparison models is achieved.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Geochemistry & Geophysics
Libao Zhang, Jie Ma
Summary: The PSL method combines the advantages of weakly and fully supervised learning, achieving object detection in remote sensing images through a progressive learning approach, addressing concerns about boundary maintenance and postprocessing efficiency.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Computer Science, Information Systems
Xingzheng Wang, Songwei Chen, Jiehao Liu, Guoyao Wei
Summary: The current light-field salient object detection methods lack edge details, which affect the performance of subsequent computer vision tasks. To address this, a novel convolutional neural network is proposed to accurately detect salient objects by extracting effective edge information from light-field data. Extensive evaluations demonstrate the effectiveness of the proposed method.
Article
Computer Science, Artificial Intelligence
Xi Chen, Chaojie Wang, Zhihong Li, Min Liu, Qingli Li, Honggang Qi, Dongliang Ma, Zhiqiang Li, Yong Wang
Summary: Object detection in large aerial images often requires splitting each image into local images, which may lead to deficiencies in contextual information and incomplete detection of oversized objects. Existing object detection methods for large images are limited in applicability due to their complex additional structures or training steps. To address these problems, a Coupled Global-Local (CGL) network is proposed, which can be easily embedded in frequently used detection models to efficiently capture more information.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Xiaofei Zhou, Hao Fang, Zhi Liu, Bolun Zheng, Yaoqi Sun, Jiyong Zhang, Chenggang Yan
Summary: This article proposes an end-to-end dense attention-guided cascaded network (DACNet) for the detection of salient objects (i.e., defects) on strip steel surfaces. DACNet is a U-shape network consisting of an encoder and a decoder. The encoder deploys multi-resolution convolutional branches in a cascaded way to fuse deep features, while the decoder integrates the multi-scale deep features into the saliency map using a dense attention mechanism. Experimental results show that our model outperforms state-of-the-art models in all evaluation metrics.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Geochemistry & Geophysics
Gong Cheng, Bowei Yan, Peizhen Shi, Ke Li, Xiwen Yao, Lei Guo, Junwei Han
Summary: This article focuses on the main challenges of few-shot object detection in remote sensing images and proposes a simple yet effective method named P-CNN, which consists of a prototype learning network, a prototype-guided region proposal network, and a detector head to overcome the challenges.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Xin Wang, Zhilu Zhang, Shihan Jing, Huiyu Zhou
Summary: In this paper, a novel end-to-end network called AATBNet is proposed for salient object detection in optical remote sensing images. The AATBNet includes an attention feature encoding branch, a hierarchical feature decoding branch, and a two losses computation branch, which effectively and robustly computes saliency maps and salient edge maps. Experimental results on two RSI benchmarks and comparisons with 20 state-of-the-art technologies demonstrate the superiority of our AATBNet.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Computer Science, Artificial Intelligence
Zhengyun Zhao, Ziqing Huang, Xiuli Chai, Jun Wang
Summary: In this study, we propose a depth enhanced cross-modal cascaded network (DCCNet) for RGB-D SOD. The network enhances the quality of depth images using a depth preprocessing algorithm and extracts features using cascaded cross-modal guided modules and adaptive residual selection modules. A cross-modal channel-wise refinement is utilized to fuse top-level features from different modal branches, and network training is optimized using a multiscale loss. Experimental results demonstrate that DCCNet performs comparably to state-of-the-art RGB-D SOD methods on six common datasets.
NEURAL PROCESSING LETTERS
(2023)
Article
Computer Science, Information Systems
Chen Huang, Tingfa Xu, Yuhan Zhang, Chenguang Pan, Jianhua Hao, Xiangmin Li
Summary: The proposed salient object detection model on hyperspectral images in wireless network utilizes saliency optimization on convolutional neural network (CNN) features to extract spatial and spectral features for effective detection. The model generates final saliency maps by optimizing saliency values of foreground and background cues, showing better performance on hyperspectral images.
Article
Computer Science, Artificial Intelligence
Tianyou Chen, Xiaoguang Hu, Jin Xiao, Guofeng Zhang, Shaojie Wang
Summary: Compared with RGB salient object detection (SOD) methods, RGB-D SOD models show better performance by leveraging spatial information in depth maps. However, existing models often ignore modality-specific characteristics and simply fuse multi-modal features. This paper proposes CFIDNet, a novel network that addresses this issue by enhancing depth cues and refining multi-level features. Experimental results demonstrate that CFIDNet achieves highly competitive performance over 15 state-of-the-art models.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Environmental Sciences
Zitong Wu, Biao Hou, Bo Ren, Zhongle Ren, Shuang Wang, Licheng Jiao
Summary: A new ship detection network called ISASDNet, utilizing a two-stage detection network structure with object and pixel branches, global relational inference layers, and a global reasoning module for improved instance segmentation results of ships. The MASDM module and a specific strategy further enhance the performance of detection results.
Article
Computer Science, Artificial Intelligence
Mingchen Zhuge, Deng-Ping Fan, Nian Liu, Dingwen Zhang, Dong Xu, Ling Shao
Summary: Although current salient object detection (SOD) works have made significant progress, they are limited in preserving the integrity of predicted salient regions. To address this issue, a novel Integrity Cognition Network (ICON) is proposed, which leverages diverse feature aggregation, integrity channel enhancement, and part-whole verification to learn strong integrity features. Experimental results on seven benchmarks demonstrate that ICON outperforms baseline methods and achieves around 10% improvement in average false negative ratio (FNR). The code and results are available at: https://github.com/mczhuge/ICON.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Chemistry, Analytical
Xiaolian Liao, Jun Li, Leyi Li, Caoxi Shangguan, Shaoyan Huang
Summary: In this paper, we propose a RGBD salient object detection method based on specific object imaging, which can accurately detect and image salient objects by capturing and processing complete object feature information.
Article
Computer Science, Artificial Intelligence
Guang-Hai Liu, Zuo-Yong Li, Jing-Yu Yang, David Zhang
Summary: This article introduces a novel image retrieval method that improves retrieval performance by using sublimated deep features. The method incorporates orientation-selective features and color perceptual features, effectively mimicking these mechanisms to provide a more discriminating representation.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Fengguang Peng, Zihan Ding, Ziming Chen, Gang Wang, Tianrui Hui, Si Liu, Hang Shi
Summary: RGB-Thermal (RGB-T) semantic segmentation is an emerging task that aims to improve the robustness of segmentation methods under extreme imaging conditions by using thermal infrared modality. The challenges of foreground-background distinguishment and complementary information mining are addressed by proposing a cross modulation process with two collaborative components. Experimental results show that the proposed method achieves state-of-the-art performances on current RGB-T segmentation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Baihong Han, Xiaoyan Jiang, Zhijun Fang, Hamido Fujita, Yongbin Gao
Summary: This paper proposes a novel automatic prompt generation method called F-SCP, which focuses on generating accurate prompts for low-accuracy classes and similar classes. Experimental results show that our approach outperforms state-of-the-art methods on six multi-domain datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Huikai Liu, Ao Zhang, Wenqian Zhu, Bin Fu, Bingjian Ding, Shengwu Xiong
Summary: Adverse weather conditions present challenges for computer vision tasks, and image de-weathering is an important component of image restoration. This paper proposes a multi-patch skip-forward structure and a Residual Deformable Convolutional module to improve feature extraction and pixel-wise reconstruction.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Oliver M. Crook, Mihai Cucuringu, Tim Hurst, Carola-Bibiane Schonlieb, Matthew Thorpe, Konstantinos C. Zygalakis
Summary: The transportation LP distance (TLP) is a generalization of the Wasserstein WP distance that can be applied directly to color or multi-channelled images, as well as multivariate time-series. TLP interprets signals as functions, while WP interprets signals as measures. Although both distances are powerful tools in modeling data with spatial or temporal perturbations, their computational cost can be prohibitively high for moderate pattern recognition tasks. The linear Wasserstein distance offers a method for projecting signals into a Euclidean space, and in this study, we propose linear versions of the TLP distance (LTLP) that show significant improvement over the linear WP distance in signal processing tasks while being several orders of magnitude faster to compute than the TLP distance.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Haitao Tian, Shiru Qu, Pierre Payeur
Summary: This paper proposes a method of target-dependent classifier, which optimizes the joint hypothesis of domain adaptation into a target-dependent hypothesis that better fits with the target domain clusters through an unsupervised fine-tuning strategy and the concept of meta-learning. Experimental results demonstrate that this method outperforms existing techniques in synthetic-to-real adaptation and cross-city adaptation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Qingsen Yan, Axi Niu, Chaoqun Wang, Wei Dong, Marcin Wozniak, Yanning Zhang
Summary: Deep learning-based methods have achieved remarkable results in the field of super-resolution. However, the limitation of paired training image sets has led researchers to explore self-supervised learning. However, the assumption of inaccurate downscaling kernel functions often leads to degraded results. To address this issue, this paper introduces KGSR, a kernel-guided network that trains both upscaling and downscaling networks to generate high-quality high-resolution images even without knowing the actual downscaling process.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Yifan Chen, Xuelong Li
Summary: Gait recognition is a popular technology for identification due to its ability to capture gait features over long distances without cooperation. However, current methods face challenges as they use a single network to extract both temporal and spatial features. To solve this problem, we propose a two-branch network that focuses on spatial and temporal feature extraction separately. By combining these features, we can effectively learn the spatio-temporal information of gait sequences.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Wei Shi, Wentao Zhang, Wei-shi Zheng, Ruixuan Wang
Summary: This article proposes a simple yet effective visualization framework called PAMI, which does not require detailed model structure and parameters to obtain visualization results. It can be applied to various prediction tasks with different model backbones and input formats.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Xiaobo Hu, Jianbo Su, Jun Zhang
Summary: This paper reviews the latest technologies in pattern recognition, highlighting their instabilities and failures in practical applications. From a control perspective, the significance of disturbance rejection in pattern recognition is discussed, and the existing problems are summarized. Finally, potential solutions related to the application of compensation on features are discussed to emphasize future research directions.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Andres Felipe Posada-Moreno, Nikita Surya, Sebastian Trimpe
Summary: Convolutional neural networks are widely used in critical systems, and explainable artificial intelligence has proposed methods for generating high-level explanations. However, these methods lack the ability to determine the location of concepts. To address this, we propose a novel method for automatic concept extraction and localization based on pixel-wise aggregations, and validate it using synthetic datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Peng Bao, Jianian Li, Rong Yan, Zhongyi Liu
Summary: In this paper, a novel Dynamic Graph Contrastive Learning framework, DyGCL, is proposed to capture the temporal consistency in dynamic graphs and achieve good performance in node representation learning.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Kristian Schultz, Saptarshi Bej, Waldemar Hahn, Markus Wolfien, Prashant Srivastava, Olaf Wolkenhauer
Summary: Research indicates that deep generative models perform poorly compared to linear interpolation-based methods for synthetic data generation on small, imbalanced tabular datasets. To address this, a new approach called ConvGeN, combining convex space learning with deep generative models, has been proposed. ConvGeN improves imbalanced classification on small datasets while remaining competitive with existing linear interpolation methods.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Khondaker Tasrif Noor, Antonio Robles-Kelly
Summary: In this paper, the authors propose H-CapsNet, a capsule network designed for hierarchical image classification. The network effectively captures hierarchical relationships using dedicated capsules for each class hierarchy. A modified hinge loss is utilized to enforce consistency among the involved hierarchies. Additionally, a strategy for dynamically adjusting training parameters is presented to achieve better balance between the class hierarchies. Experimental results demonstrate that H-CapsNet outperforms competing hierarchical classification networks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Lei Liu, Guorun Li, Yuefeng Du, Xiaoyu Li, Xiuheng Wu, Zhi Qiao, Tianyi Wang
Summary: This study proposes a new agricultural image segmentation model called CS-Net, which uses Simple-Attention Block and Simpleformer to improve accuracy and inference speed, and addresses the issue of performance collapse of Transformers in agricultural image processing.
PATTERN RECOGNITION
(2024)