Search

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]

Capturing the comprehensive information of various sizes and shapes of images in the same convolution layer is typically a challenging task in computer vision. There are two main kinds of methods for capturing those features. The first uses the inception structure and its variants. The second utilizes larger convolution kernels on specific layers or stacks with more convolution blocks. However, these methods can result in computationally intensive or vanishing gradients. In this paper, to accommodate feature distributions with different sizes, shapes and reduce computational cost, we propose a width- and depth-aware module named the WD-module to match feature distributions. Moreover, the proposed WD-module consumes less computational cost and parameters compared with traditional residual convolution layers. To verify the effectiveness of our proposed method, a size- and shape-aware backbone network named S2A-Net was built, which was obtained by stacking the WD-modules. By visualizing heat maps and features, the proposed S2A-Net can adapt to objects with different sizes and shapes in visual recognition tasks and learn more comprehensive characteristics. Experimental results show that the proposed method has higher accuracy in image recognition and outperforms other state-of-the-art networks with the same numbers of layers. • A width-aware and deep-aware module is build. • A size-aware and shape-aware network for visual recognition is build. • Compared with other state-of-the-art methods, the proposed method can achieve better results while consume less parameters and FLOPs. [ABSTRACT FROM AUTHOR]