Local and Global Feature Aggregation-Aware Network for Salient Object Detection

With the rise of deep learning technology, salient object detection algorithms based on convolutional neural networks (CNNs) are gradually replacing traditional methods. The majority of existing studies, however, focused on the integration of multi-scale features, thereby ignoring the characteristics of other significant features. To address this problem, we fully utilized the features to alleviate redundancy. In this paper, a novel CNN named local and global feature aggregation-aware network (LGFAN) has been proposed. It is a combination of the visual geometry group backbone for feature extraction, an attention module for high-quality feature filtering, and an aggregation module with a mechanism for rich salient features to ease the dilution process on the top-down pathway. Experimental results on five public datasets demonstrated that the proposed method improves computational efficiency while maintaining favorable performance.

Multi-Scale Feature Aggregation Network for Water Area Segmentation

Water area segmentation is an important branch of remote sensing image segmentation, but in reality, most water area images have complex and diverse backgrounds. Traditional detection methods cannot accurately identify small tributaries due to incomplete mining and insufficient utilization of semantic information, and the edge information of segmentation is rough. To solve the above problems, we propose a multi-scale feature aggregation network. In order to improve the ability of the network to process boundary information, we design a deep feature extraction module using a multi-scale pyramid to extract features, combined with the designed attention mechanism and strip convolution, extraction of multi-scale deep semantic information and enhancement of spatial and location information. Then, the multi-branch aggregation module is used to interact with different scale features to enhance the positioning information of the pixels. Finally, the two high-performance branches designed in the Feature Fusion Upsample module are used to deeply extract the semantic information of the image, and the deep information is fused with the shallow information generated by the multi-branch module to improve the ability of the network. Global and local features are used to determine the location distribution of each image category. The experimental results show that the accuracy of the segmentation method in this paper is better than that in the previous detection methods, and has important practical significance for the actual water area segmentation.

Urban street scene analysis using lightweight multi-level multi-path feature aggregation network

Urban street scene analysis is an important problem in computer vision with many off-line models achieving outstanding semantic segmentation results. However, it is an ongoing challenge for the research community to develop and optimize the deep neural architecture with real-time low computing requirements whilst maintaining good performance. Balancing between model complexity and performance has been a major hurdle with many models dropping too much accuracy for a slight reduction in model size and unable to handle high-resolution input images. The study aims to address this issue with a novel model, named M2FANet, that provides a much better balance between model’s efficiency and accuracy for scene segmentation than other alternatives. The proposed optimised backbone helps to increase model’s efficiency whereas, suggested Multi-level Multi-path (M2) feature aggregation approach enhances model’s performance in the real-time environment. By exploiting multi-feature scaling technique, M2FANet produces state-of-the-art results in resource-constrained situations by handling full input resolution. On the Cityscapes benchmark data set, the proposed model produces 68.5% and 68.3% class accuracy on validation and test sets respectively, whilst having only 1.3 million parameters. Compared with all real-time models of less than 5 million parameters, the proposed model is the most competitive in both performance and real-time capability.

AFGL-Net: Attentive Fusion of Global and Local Deep Features for Building Façades Parsing

In this paper, we propose a deep learning framework, namely AFGL-Net to achieve building façade parsing, i.e., obtaining the semantics of small components of building façade, such as windows and doors. To this end, we present an autoencoder embedding position and direction encoding for local feature encoding. The autoencoder enhances the local feature aggregation and augments the representation of skeleton features of windows and doors. We also integrate the Transformer into AFGL-Net to infer the geometric shapes and structural arrangements of façade components and capture the global contextual features. These global features can help recognize inapparent windows/doors from the façade points corrupted with noise, outliers, occlusions, and irregularities. The attention-based feature fusion mechanism is finally employed to obtain more informative features by simultaneously considering local geometric details and the global contexts. The proposed AFGL-Net is comprehensively evaluated on Dublin and RueMonge2014 benchmarks, achieving 67.02% and 59.80% mIoU, respectively. We also demonstrate the superiority of the proposed AFGL-Net by comparing with the state-of-the-art methods and various ablation studies.

Pyramid-Net: Intra-layer Pyramid-Scale Feature Aggregation Network for Retinal Vessel Segmentation

Retinal vessel segmentation plays an important role in the diagnosis of eye-related diseases and biomarkers discovery. Existing works perform multi-scale feature aggregation in an inter-layer manner, namely inter-layer feature aggregation. However, such an approach only fuses features at either a lower scale or a higher scale, which may result in a limited segmentation performance, especially on thin vessels. This discovery motivates us to fuse multi-scale features in each layer, intra-layer feature aggregation, to mitigate the problem. Therefore, in this paper, we propose Pyramid-Net for accurate retinal vessel segmentation, which features intra-layer pyramid-scale aggregation blocks (IPABs). At each layer, IPABs generate two associated branches at a higher scale and a lower scale, respectively, and the two with the main branch at the current scale operate in a pyramid-scale manner. Three further enhancements including pyramid inputs enhancement, deep pyramid supervision, and pyramid skip connections are proposed to boost the performance. We have evaluated Pyramid-Net on three public retinal fundus photography datasets (DRIVE, STARE, and CHASE-DB1). The experimental results show that Pyramid-Net can effectively improve the segmentation performance especially on thin vessels, and outperforms the current state-of-the-art methods on all the adopted three datasets. In addition, our method is more efficient than existing methods with a large reduction in computational cost. We have released the source code at https://github.com/JerRuy/Pyramid-Net.