Significant efforts have been made to develop techniques for extracting useful information from remote sensing (RS) images in view of their favorable properties such as wide coverage, good timeliness and large content. Such techniques often involve scene classification, which provides an effective way to interpret RS data. However, large intra-class variances and high inter-class similarities make remote sensing scene classification (RSSC) a tough task. Recently, deep learning has been brought to bear upon RSSC. Deep models with ever-improving classification accuracy are continually being put forward. This letter shifts focus from network structure optimization to the loss function and takes a principled approach based on optimal transport (OT). OT measures the divergence between two probability distributions by computing the minimum cost of converting one distribution to the other, which can help discriminate different data clusters in high-dimensional feature spaces. Relaxation of marginal constraints during computation of OT objective can accommodate certain potentially desirable transportation plans that are otherwise inadmissible. However, the effect of OT objective is sensitive to the extent of marginal relaxation. In this work, we propose a method, named exact marginal relaxation robust optimal transport (EMRROT), to estimate the optimal threshold for marginal relaxation and investigate its application to RSSC. Experimental results show that the proposed EMRROT achieves highly competitive performances on the benchmark RSSC datasets.

In recent years, hashing methods have been popular in the large-scale media search for low storage and strong representation capabilities. To describe objects with similar overall appearance but subtle differences, more and more studies focus on hashing-based fine-grained image retrieval. Existing hashing networks usually generate both local and global features through attention guidance on the same deep activation tensor, which limits the diversity of feature representations. To handle this limitation, we substitute convolutional descriptors for attention-guided features and propose an Attributes Grouping and Mining Hashing (AGMH), which groups and embeds the category-specific visual attributes in multiple descriptors to generate a comprehensive feature representation for efficient fine-grained image retrieval. Specifically, an Attention Dispersion Loss (ADL) is designed to force the descriptors to attend to various local regions and capture diverse subtle details. Moreover, we propose a Stepwise Interactive External Attention (SIEA) to mine critical attributes in each descriptor and construct correlations between fine-grained attributes and objects. The attention mechanism is dedicated to learning discrete attributes, which will not cost additional computations in hash codes generation. Finally, the compact binary codes are learned by preserving pairwise similarities. Experimental results demonstrate that AGMH consistently yields the best performance against state-of-the-art methods on fine-grained benchmark datasets.

Smoke in remote sensing (RS) images is regarded as the indicator of fire disasters and it is vital to distinguish smoke from other RS scenes. Convolutional neural network (CNN) based classification networks have viewed great success but the cross-entropy loss may suffer from domain gap when training data and testing data do not follow independent and identical distributions. Served as an objective function, the optimal transport (OT) distance is able to tackle the domain gap by aligning two distributions in domain adaptation tasks. Generally speaking, the OT-based algorithms can be divided into two categories: methods that compute OT distance on minibatches, and methods which rely on the adversarial training. In this letter, we propose a hybrid OT algorithm, termed Joint MiniBatch and Adversarial Optimal Transport (JMBAOT), to eliminate the domain gap for cross-scene classification of RS smoke-related scenes. JMBAOT takes advantages of both the minibatch and adversarial OT to better distinguish different classes on the feature space and improve the performance of domain adaptation. In a large amount of experiments, JMBAOT shows its effectiveness and achieves the state-of-the-art (SOTA) performance.

Remote sensing (RS) images are used in a wide range of tasks. In the fire detection field, smoke in RS images is considered as an indicator of wildfires. However, smoke-like scenes, e.g., cloud, in RS images increase the difficulty of smoke recognition. Convolutional neural networks (CNNs) have greatly promoted the development of image processing. CNNs are good at capturing local features; however, their ability to capture global features is relatively weak. Recently, the transformer deep learning model has shown strong potential in vision tasks. The transformer model utilizes self-attention modules to extract global features but may lose local details. Recognition of smoke in RS images depends strongly on the combination of both local and global features. Thus, this article proposes the transformer enhanced convolutional network (TECN) to classify RS smoke-like scenes. The proposed hybrid TECN model exploits the advantages of the CNN and transformer techniques at the same time. In TECN, the feature merge and intelligent aggregation modules are used to promote conversion and aggregation between CNN feature maps and transformer patch embeddings. Experiments are conducted on the USTC_SmokeRS dataset, which is developed for the classification of RS smoke-like scenes. The experimental results demonstrate that the proposed TECN achieves a competitive accuracy of 98.39% on this dataset.

This paper initiates a systematic methodology for real-time chaos-based video encryption and decryption communications on the system design and algorithm analysis. The proposed system design and algorithm analysis have been validated on an FPGA hardware platform via Verilog Hardware Description Language (Verilog HDL). Based on the fundamental anti-control principles of dynamical systems, a 6-D real domain chaotic system is designed, and then the corresponding Verilog HDL algorithm is developed. The proposed Verilog HDL algorithm is utilized to design a real-time chaos-based secure video communication system, with a generalized design principle derived, which is implemented on an FPGA hardware platform equipped with an XUP Virtex-II chip. Following this line, the designed working mechanism is demonstrated by hardware experiments. The security performance is tested using the TESTU01 statistical test suites, the differential analysis, and the sensitivity of key parameters mismatch. Both theoretical analysis and experimental results validate the feasibility and reliability of the proposed system.

Constructing program invariants is one of the key problems of program verification. A lot of approaches to invariant generation have been reported, and all of these methods assume that program variables are evaluated over infinite domains such as rational or integer. Actually, during the execution of program, all variables are expressed using bit-vectors with limited width and evaluated over finite domains. Many invariants suit for infinite domains may be invalid in finite domains, and vice versa. This paper proposes an approach to construct invariants for program whose variables are evaluated over finite domains. This method translates a program into constraints that are solved using a QBF (Quantified Boolean Formula) solver to yield desired program invariants. It can be used to discover a rich class of invariants including linear (or polynomial) equality (or inequality) invariants involving operations like addition, multiplication, division, shift, bitwise operation, even quantifiers. And we also show how this technique can be used to prove partial correctness, termination and total correctness.