Deep learning models have been proven to be susceptible to malicious adversarial attacks, which manipulate input images to deceive the model into making erroneous decisions. Consequently, the threat posed to these models serves as a poignant reminder of the necessity to focus on the model security of object segmentation algorithms based on deep learning. However, the current landscape of research on adversarial attacks primarily centers around static images, resulting in a dearth of studies on adversarial attacks targeting Video Object Segmentation (VOS) models. Given that a majority of self-supervised VOS models rely on affinity matrices to learn feature representations of video sequences and achieve robust pixel correspondence, our investigation has delved into the impact of adversarial attacks on self-supervised VOS models. In response, we propose an innovative black-box attack method incorporating contrastive loss. This method induces segmentation errors in the model through perturbations in the feature space and the application of a pixel-level loss function. Diverging from conventional gradient-based attack techniques, we adopt an iterative black-box attack strategy that incorporates contrastive loss across the current frame, any two consecutive frames, and multiple frames. Through extensive experimentation conducted on the DAVIS 2016 and DAVIS 2017 datasets using three self-supervised VOS models and one unsupervised VOS model, we unequivocally demonstrate the potent attack efficiency of the black-box approach. Remarkably, theJ&Fmetric value experiences a significant decline of up to 50.08% post-attack.

Video Object Segmentation (VOS) methods have made many breakthroughs with the help of the continuous development and advancement of deep learning. However, the deep learning model is vulnerable to malicious adversarial attacks, which mislead the model to make wrong decisions by adding adversarial perturbation that humans cannot perceive to the input image. Threats to deep learning models remind us that video object segmentation methods are also vulnerable to attacks, thereby threatening their security. Therefore, we study adversarial attacks on the VOS task to better identify the vulnerabilities of the VOS method, which in turn provides an opportunity to improve its robustness. In this paper, we propose an attention-guided adversarial attack method, which uses spatial attention blocks to capture features with global dependencies to construct correlations between consecutive video frames, and performs multipath aggregation to effectively integrate spatial-temporal perturbation, thereby guiding the deconvolution network to generate adversarial examples with strong attack capability. Specifically, the class loss function is designed to enable the deconvolution network to better activate noise in other regions and suppress the activation related to the object class based on the enhanced feature map of the object class. At the same time, attentional feature loss is designed to enhance the transferability against attack. The experimental results on the DAVIS dataset show that the proposed attention-guided adversarial attack method can significantly reduce the segmentation accuracy of OSVOS, and the J & F mean on DAVIS 2016 can reach 73.6% drop rate. The generated adversarial examples are also highly transferable to other video object segmentation models.

In person re-identification (Re-ID) , the data annotation cost of supervised learning, is huge and it cannot adapt well to complex situations. Therefore, compared with supervised deep learning methods, unsupervised methods are more in line with actual needs. In unsupervised learning, a key to solving Re-ID is to find a standard that can effectively distinguish the difference (distance) between the features of images belonging to different pedestrian identities. However, there are some differences in the images captured by different cameras (such as brightness, angle, etc.). It is well known that the training of neural networks is mainly based on the distance between features, while in unsupervised learning, especially in unsupervised learning methods based on hierarchical clustering, the distance between features plays a more important role in the clustering phase. We improve the accuracy of a deep learning method based on hierarchical clustering under fully unsupervised conditions, starting from both feature and distance metrics. First, we propose to use spherical features, by normalizing the images in the feature space, to weaken the structural differences (length) between features, while saving the feature differences (direction) between different identities. Then, we use the sum of squared errors (SSE) as a regularization term to balance different cluster states. We evaluate our method on four large-scale Re-ID datasets, and experiments show that our method achieves better results than the state-of-the-art unsupervised methods.

Remote sensing image scene classification has achieved significant breakthroughs in recent years. However, due to the high complexity and expensive computation most of CNNs used in the field of remote sensing imagery scene classification, it has become a challenging task for extracting effective features at restricted hardware conditions. To solve this problem, we present a model compression method by means of evolutionary algorithms. Specifically, we compress the model by pruning filters and transform the compression of the CNN model into a multi-objective optimization problem based on classification accuracy and compression ratio by using the adaptive-BN-based evaluation method. Furthermore, the prior knowledge of ResNet-50 on ImageNet is introduced to reduce the instability of evolutionary algorithm as a result of random population initialization. Experiments are implemented on three datasets with two evolutionary algorithms, and results demonstrate that our method can achieve state-of-the-art performances.

The ever‐developing Internet of Things (IoT) drives the prosperity of ubiquitous connections among heterogeneous wireless devices (e.g. WiFi, ZigBee and Bluetooth) that follow different standards. Wireless devices share unlicensed industrial, scientific and medical bands, offering an opportunity for cross‐technology communication (CTC), where coexistence and cooperation mechanisms of wireless technologies incur the problem of coexistence. This study is purposed to present a rounded state‐of‐the‐art survey on CTC from the hardware perspective, CTC techniques are roughly divided into two types: hardware based and hardware free. In hardware‐based strategies, a dedicated hardware is required to send information to wireless devices for enabling direct communication. The hardware‐free schemes, by contrast, enable heterogeneous wireless devices to communicate directly by exchanging information or data without the dedicated hardware. Recent advances in CTC are reviewed in both types by expatiating on how heterogeneous wireless devices are achieving direct communication. The authors compare some CTCs with respect to throughput, communication range, energy efficiency and cost, in addition, they present open research issues of two types.