Remote Sensing Change Detection (RSCD) plays a crucial role in various earth observation tasks. Recently, deep learning-based methods have been widely employed for CD due to their exceptional performance. Although, existing approaches can detect obviously changed regions easily, they suffer from difficulties in dealing with pseudo-changes caused by lighting condition changes, season changes and complex land cover conditions. To tackle this challenge, we propose a CD network using visual-prompt enhanced CLIP (CVNet), which incorporates the foundation model CLIP into the RSCD task to leverage its semantic information for identifying pseudochange regions. Specifically, we use CLIP visual encoder with transformer-structure to enhance single-time features extracted by ResNet. To ensure effective transfer ability for downstream tasks while considering computational cost, we fine-tune CLIP using a visual prompt. In addition, to efficiently enhance features extracted by ResNet, we design a CLIP-guided feature refinement (CGFR) module that adaptively integrates both types of features. Furthermore, a transformer encoder structure is introduced to get change information for dual-time images and a transformer decoder is introduced to propagate change information back. To test the performance of our proposed model, we conduct experiments on two datasets, including LEVIR-CD and WHU-CD. The experimental results show that our model can outperform several state-of-the-art models on both datasets. The code is available at https://github.com/Hyper-Baller/CVNet.

Analogies between codes and lattices have been extensively studied for the last decades. In this context, the MacWilliams identity is the finite analog of the Jacobi-Poisson summation formula of the theta function. Motivated by the random lattice theory, the statistical significance of MacWilliams theorem is considered. Indeed, the MacWilliams distribution provides a finite analog of the classical Gauss distribution. In particular, the MacWilliams distribution over quotient space of a code is statistically close to the uniform distribution. In the context of lattices, the analogy of MacWilliams identity associated with nu-function was conjectured by Solé in 1995. We give an answer to this problem.

This paper introduces a privacy-preserving distributed learning framework via private-key homomorphic encryption. Using randomness in the quantization of gradients, our encryption replaces the Gaussian error term of Learning With Errors (LWE) with quantized gradients, thus reducing the error expansion speed in conventional LWE-based homomorphic en-cryption. The proposed system allows a large number of learning participants to engage in distributed learning collaboratively over an honest-but-curious server, while ensuring the cryptographic security of participants' uploaded gradients.

Abstract Lattice-based digital signature has become one of the widely recognized post-quantum algorithms because of its simple algebraic operation, rich mathematical foundation and worst-case security, and also an important tool for constructing cryptography. This survey explores lattice-based digital signatures, a promising post-quantum resistant alternative to traditional schemes relying on factoring or discrete logarithm problems, which face increasing risks from quantum computing. The study covers conventional paradigms like Hash-and-Sign and Fiat-Shamir, as well as specialized applications including group, ring, blind, and proxy signatures. It analyzes the versatility and security strengths of lattice-based schemes, providing practical insights. Each chapter summarizes advancements in schemes, identifying emerging trends. We also pinpoint future directions to deploy lattice-based digital signatures including quantum cryptography.

Vision-based vehicle lateral localization has been extensively studied in the literature. However, it faces great challenges when dealing with occlusion situations where the road is frequently occluded by moving/static objects. To address the occlusion problem, we propose a highly robust lateral localization framework called multilevel robust network (MLRN) in this article. MLRN utilizes three deep neural networks (DNNs) to reduce the impact of occluding objects on localization performance from the object, feature, and decision levels, respectively, which shows strong robustness to varying degrees of road occlusion. At the object level, an attention-guided network (AGNet) is designed to achieve accurate road detection by paying more attention to the interested road area. Then, at the feature level, a lateral-connection fully convolutional denoising autoencoder (LC-FCDAE) is proposed to learn robust location features from the road area. Finally, at the decision level, a long short-term memory (LSTM) network is used to enhance the prediction accuracy of lateral position by establishing the temporal correlations of positioning decisions. Experimental results validate the effectiveness of the proposed framework in improving the reliability and accuracy of vehicle lateral localization.

This article proposes a novel visual measurement framework, multimodule cascaded deep neural network (MMC-DNN), to achieve accurate, reliable, and cost-effective vehicle positioning in complex urban environments. The MMC-DNN is inspired by the mechanism of the human eyes' lateral positioning, which consists of three modules called siamesed fully convolutional network (S-FCN), skip-connection fully convolutional autoencoder (SC-FCAE), and multitask neural network regressor (MT-NNR), respectively. The S-FCN is first designed to accurately detect the road area. Then, the segmented road was executed inverse perspective mapping and the result is fed to the developed SC-FCAE for extracting equivalent positioning features. Furthermore, the MT-NNR is proposed to efficiently estimate lateral position and yaw angle with the help of a road map. Based on the estimation results, the MEMS INS/GPS integration is significantly augmented by extended Kalman filter. Experimental results validate the effectiveness of the proposed framework in enhancing positioning performance.

Reliable estimation of vehicle lateral position plays an essential role in enhancing the safety of autonomous vehicles. However, it remains a challenging problem due to the frequently occurred road occlusion and the unreliability of employed reference objects (e.g., lane markings, curbs, etc.). Most existing works can only solve part of the problem, resulting in unsatisfactory performance. This paper proposes a novel deep inference network (DINet) to estimate vehicle lateral position, which can adequately address the challenges. DINet integrates three deep neural network (DNN)-based components in a human-like manner. A road area detection and occluding object segmentation (RADOOS) model focuses on detecting road areas and segmenting occluding objects on the road. A road area reconstruction (RAR) model tries to reconstruct the corrupted road area to a complete one as realistic as possible, by inferring missing road regions conditioned on the occluding objects segmented before. A lateral position estimator (LPE) model estimates the position from the reconstructed road area. To verify the effectiveness of DINet, road-test experiments were carried out in the scenarios with different degrees of occlusion. The experimental results demonstrate that DINet can obtain reliable and accurate (centimeter-level) lateral position even in severe road occlusion.