Search

Deep convolutional neural networks (DCNNs) have exhibited excellent feature extraction and detail reconstruction capabilities for single image super-resolution (SISR). Nevertheless, most previous DCNN-based methods do not fully utilize the complementary strengths between feature maps, channels, and pixels. Therefore, it hinders the ability of DCNNs to represent abundant features. To tackle the aforementioned issues, we present a Cascaded Visual Attention Network for SISR called CVANet, which simulates the visual attention mechanism of the human eyes to focus on the reconstruction process of details. Specifically, we first designed a trainable feature attention module (FAM) for feature-level attention learning. Afterward, we introduce a channel attention module (CAM) to reinforce feature maps under channel-level attention learning. Meanwhile, we propose a pixel attention module (PAM) that adaptively selects representative features from the previous layers, which are utilized to generate a high-resolution image. Satisfactory, our CVANet can effectively improve the resolution of images by exploring the feature representation capabilities of different modules and the visual perception properties of the human eyes. Extensive experiments with different methods on four benchmarks demonstrate that our CVANet outperforms the state-of-the-art (SOTA) methods in subjective visual perception, PSNR, and SSIM.The code will be made available https://github.com/WilyZhao8/CVANet. [ABSTRACT FROM AUTHOR]

Siamese-architecture-based self-supervised learning usually suffers from relatively high computational consumption and unsatisfactory performance because of its slow convergence and poor feature extraction capability. To alleviate these issues, we propose a self-supervised method, called SSL 2 , that is both efficient and effective. Specifically, a global and local sampling method is proposed to increase the number of samples while maintaining connections between semantic features. More significantly, SSL 2 maintains low computational complexity and facilitates the establishment of mapping relationships between global comprehensive and local detailed features compared with other methods. In addition, an i nformation r etainer p rojection h ead (IRPH) is proposed to further balance the information between detailed inconsistency and semantic consistency. Finally, hybrid tasks are embedded into SSL 2 to optimize the model so that it can effectively leverage the data provided by global and local sampling. Extensive qualitative and quantitative evaluations of various types of benchmarks illustrate that SSL 2 outperforms existing self-supervised frameworks in commonly used computer vision tasks. Specifically, SSL 2 achieved satisfactory performance with linear classification on ImageNet, outperforming MoCo-v2 by 2.2% with fewer calculations, and it also achieved competitive results compared with other state-of-the-art methods. • A new single-branch self-supervised learning framework is designed. • A novel sampling strategy is designed to make full use of the information. • A head is designed to balance detailed inconsistency and semantic consistency. • Well-balanced hybrid loss functions are introduced. [ABSTRACT FROM AUTHOR]

Ideal wheat grain quality detection systems aim for rapid and precise recognition of flaws. Computer vision and machine learning have been widely studied as potential alternatives to human inspection. Numerous deep learning-based detection and classification methods have been proposed in the last few years. However, these methods suffer from poor performance and extremely long time consumption due to the weak feature extraction ability and high computational overhead. To solve these challenges, we present the first comprehensive study and analysis of wheat grain detection using improved YOLOv5. Specifically, we design a machine vision system and construct a Wheat Grain Detection Benchmark (WGDB) including 1746 images with 7844 bounding boxes, all of which have been independently classified. Utilizing this dataset, we conduct a comprehensive study of the most advanced objection detection methods. In addition, we propose a Wheat Grain Detection Network (called WGNet) trained on this benchmark as a baseline, aiming to solve the degradation issues by employing sparse network pruning and a hybrid attention module. Extensive experiments demonstrate the limitations of existing methods and the improved performance of our method, which achieves state-of-the-art precision with the fastest inference speed. The constructed benchmark and the improved experiments shed light on future research in wheat grain detection. The dataset and code will be available at WGNet. • We construct a large-scale wheat grain detection benchmark. • We conduct a comprehensive study with the constructed dataset. • We propose a light-weight Wheat Grain Detection network by employing sparse network pruning and a hybrid attention module. [ABSTRACT FROM AUTHOR]

Convolutional neural network (CNN)-based self-supervised visual representation learning (SSL) is a long-standing problem achieving significant successes with traditional handcrafted pretext tasks and contrastive learning. However, existing SSL methods typically suffer from high computational overhead and poor performance due to sluggish convergence speeds and poor detail extraction capabilities. In this work, to address these issues and improve the robustness, we provide a new self-supervised architecture for incorporating a single-branch backbone with hybrid tasks into the representation learning process. Specifically, our method takes advantage of features from both intra- and inter-images by using discrete montage images. Then a single backbone with a novel A daptive D ecouple C onfusion (ADC) module is proposed to improve the feature extraction capabilities and alleviate the confusion regions in montage images. Besides, both concatenated discrete vectors and patch-based global average pooled vectors in latent space are utilized to learn local detailed features and maintain semantic consistency simultaneously. Moreover, our method is optimized by hybrid tasks and enjoys faster convergence speed due to these improvements. Extensive experiments on several datasets demonstrate the effectiveness and robustness of our method. The proposed method has 2.0% improved in linear classification to the conventional single-branch methods. [Display omitted] • A new framework SSH that leverages concatenated discrete and PGAP vectors is proposed. • An A daptive D ecouple C onfusion (ADC) module is proposed to avoid degenerate performance in existing jigsaw-based methods. • We demonstrate the advantages of the above contributions through extensive experiments. [ABSTRACT FROM AUTHOR]

The automated segmentation of Intracranial Arteries (IA) in Digital Subtraction Angiography (DSA) plays a crucial role in the quantification of vascular morphology, significantly contributing to computer-assisted stroke research and clinical practice. Current research primarily focuses on the segmentation of single-frame DSA using proprietary datasets. However, these methods face challenges due to the inherent limitation of single-frame DSA, which only partially displays vascular contrast, thereby hindering accurate vascular structure representation. In this work, we introduce DIAS, a dataset specifically developed for IA segmentation in DSA sequences. We establish a comprehensive benchmark for evaluating DIAS, covering full, weak, and semi-supervised segmentation methods. Specifically, we propose the vessel sequence segmentation network, in which the sequence feature extraction module effectively captures spatiotemporal representations of intravascular contrast, achieving intracranial artery segmentation in 2D+Time DSA sequences. For weakly-supervised IA segmentation, we propose a novel scribble learning-based image segmentation framework, which, under the guidance of scribble labels, employs cross pseudo-supervision and consistency regularization to improve the performance of the segmentation network. Furthermore, we introduce the random patch-based self-training framework, aimed at alleviating the performance constraints encountered in IA segmentation due to the limited availability of annotated DSA data. Our extensive experiments on the DIAS dataset demonstrate the effectiveness of these methods as potential baselines for future research and clinical applications. The dataset and code are publicly available at https://doi.org/10.5281/zenodo.11401368 and https://github.com/lseventeen/DIAS. • We publish the DSA-sequence intracranial artery segmentation dataset, DIAS. • We propose VSS-Net for DSA-sequence vessel segmentation. • We propose a scribble learning-based weakly-supervised segmentation framework • We propose a random patch-based self-training semi-supervised segmentation framework. [ABSTRACT FROM AUTHOR]

Hyperspectral imaging technology produces images that capture both spatial and spectral details of features, constituting a key data source in remote sensing detection. However, the accuracy of classifying hyperspectral remote sensing images is influenced by factors such as extensive data volume, high redundancy, and numerous spectral bands exhibiting significant correlation. To address these challenges, we introduce a two-layer with dual-branch 3D/2D-Attention cascade network model named DBANet. Firstly, the model employs principal component analysis to extract the raw data's primary features to reduce the data's complexity. Subsequently, the data undergoes two layers of 3D convolution and 2D convolution combined with a cascade structure of attention mechanism to fully extract the data's spatial, spectral, and textural feature information. Finally, the classification of input images is computed using a fully connected layer combined with the LogSoftmax function. Our DBANet demonstrates notable advantages in feature extraction and classification performance compared to other methods, as evidenced by the comprehensive qualitative and quantitative results of three public hyperspectral remote sensing datasets. It exhibits superior performance in the classification of hyperspectral remote-sensing images. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) based methods are widely used in identifying seeds varieties with high accuracy. However, the excessive spectral bands in HSI may contain redundant information and degrade the model performance. To address this challenge, we propose a novel feature extraction method called low rank tensor approximation (LRTA). Unlike traditional methods, LRTA extracts joint discriminative information of all wheat seeds from hyperspectral images in a 3-order tensor form, preserving intrinsic information. Our model has three key steps: extracting the region of interest from hyperspectral images and presenting average spectral information in tensor form, using LRTA to extract jointly discriminative information, and feeding this information into a classifier to identify seeds varieties. Experiments on our proposed dataset show that the proposed method has 4% improved to the conventional methods on average. Our method shows promise for improving the accuracy of seeds identification while reducing the dimensionality of HSI. [ABSTRACT FROM AUTHOR]