Salient Object Detection (SOD) is gradually applied in natural scene images. However, due to the apparent differences between optical remote sensing images and natural scene images, directly applying the SOD of natural scene images to optical remote sensing images has limited performance in global context information. Therefore, salient object detection in optical remote sensing images (ORSI-SOD) is challenging. Optical remote sensing images usually have large-scale variations. However, the vast majority of networks are based on Convolutional Neural Network (CNN) backbone networks such as VGG and ResNet, which can only extract local features. To address this problem, we designed a new model that employs a transformer-based backbone network capable of extracting global information and remote dependencies. A new framework is proposed for this question, named Global and Multiscale Aggregate Network for Saliency Object Detection in Optical Remote Sensing Images (GMANet). In this framework, the Pyramid Vision Transformer (PVT) is an encoder to catch remote dependencies. A Multiscale Attention Module (MAM) is introduced for extracting multiscale information. Meanwhile, a Global Guiled Brach (GGB) is used to learn the global context information and obtain the complete structure. Four MAMs are densely connected to this GGB. The Aggregate Refinement Module (ARM) is used to enrich the details of edge and low-level features. The ARM fuses global context information and encoder multilevel features to complement the details while the structure is complete. Extensive experiments on two public datasets show that our proposed framework GMANet outperforms 28 state-of-the-art methods on six evaluation metrics, especially E-measure and F-measure. It is because we apply a coarse-to-fine strategy to merge global context information and multiscale information.

Deep Generative Models (DGMs), as a state-of-the-art technology in the field of artificial intelligence, find extensive applications across various domains. However, their security concerns have increasingly gained prominence, particularly with regard to invisible backdoor attacks. Currently, most backdoor attack methods rely on visible backdoor triggers that are easily detectable and defendable against. Although some studies have explored invisible backdoor attacks, they often require parameter modifications and additions to the model generator, resulting in practical inconveniences. In this study, we aim to overcome these limitations by proposing a novel method for invisible backdoor attacks. We employ an encoder–decoder network to ‘poison’ the data during the preparation stage without modifying the model itself. Through meticulous design, the trigger remains visually undetectable, substantially enhancing attacker stealthiness and success rates. Consequently, this attack method poses a serious threat to the security of DGMs while presenting new challenges for security mechanisms. Therefore, we urge researchers to intensify their investigations into DGM security issues and collaboratively promote the healthy development of DGM security.

It has become a tendency to use a combination of autoencoders and graph neural networks for attribute graph clustering to solve the community detection problem. However, the existing methods do not consider the influence differences between node neighborhood information and high-order neighborhood information, and the fusion of structural and attribute features is insufficient. In order to make better use of structural information and attribute information, we propose a model named community detection fusing graph attention network (CDFG). Specifically, we firstly use an autoencoder to learn attribute features. Then the graph attention network not only calculates the influence weight of the neighborhood node on the target node but also adds the high-order neighborhood information to learn the structural features. After that, the two features are initially fused by the balance parameter. The feature fusion module extracts the hidden layer representation of the graph attention layer to calculate the self-correlation matrix, which is multiplied by the node representation obtained by the preliminary fusion to achieve secondary fusion. Finally, the self-supervision mechanism makes it face the community detection task. Experiments are conducted on six real datasets. Using four evaluation metrics, the CDFG model performs better on most datasets, especially for the networks with longer average paths and diameters and smaller clustering coefficients.

Transferring facial pose and expression features from one face to another is a challenging problem and an interesting topic in pattern recognition, but is one of great importance with many applications. However, existing models usually learn to transfer pose and expression features with classification labels, which cannot hold all the differences in shape and size between conditional faces and source faces. To solve this problem, we propose a generative adversarial network model based on classification features for facial pose and facial expression transfer. We constructed a two-stage classifier to capture the high-dimensional classification features for each face first. Then, the proposed generation model attempts to transfer pose and expression features with classification features. In addition, we successfully combined two cost functions with different convergence speeds to learn pose and expression features. Compared to state-of-the-art models, the proposed model achieved leading scores for facial pose and expression transfer on two datasets.

Most high-performance semantic segmentation networks are based on complicated deep convolutional neural networks, leading to severe latency in real-time detection. However, the state-of-the-art semantic segmentation networks with low complexity are still far from detecting objects accurately. In this paper, we propose a real-time semantic segmentation network, RecepNet, which balances accuracy and inference speed well. Our network adopts a bilateral architecture (including a detail path, a semantic path and a bilateral aggregation module). We devise a lightweight baseline network for the semantic path to gather rich semantic and spatial information. We also propose a detail stage pattern to store optimized high-resolution information after removing redundancy. Meanwhile, the effective feature-extraction structures are designed to reduce computational complexity. RecepNet achieves an accuracy of 78.65% mIoU (mean intersection over union) on the Cityscapes dataset in the multi-scale crop and flip evaluation. Its algorithm complexity is 52.12 GMACs (giga multiply–accumulate operations) and its inference speed on an RTX 3090 GPU is 50.12 fps. Moreover, we successfully applied RecepNet for blue-green algae real-time detection. We made and published a dataset consisting of aerial images of water surface with blue-green algae, on which RecepNet achieved 82.12% mIoU. To the best of our knowledge, our dataset is the world’s first public dataset of blue-green algae for semantic segmentation.