Active contour models (ACMs) have shown effectiveness on remote sensing (RS) image segmentation tasks. However, this type of method still faces two important problems when segmenting RS images. First, not using high-level semantic information makes it difficult for ACM to distinguish targets and backgrounds with similar textures. Second, the manual contour initialization required by ACMs is inconvenient and inefficient. To address the above problems, we propose a two-stage segmentation method that consists of an improved U-Net using a mixed pooling attention and an ACM (UMPA-ACM). In the first stage, a lightweight network based on U-Net structure is developed to extract semantic features while reducing computational cost. A mixed pooling attention (MPA) module is designed to enhance the ability of our proposed network to extract high-level semantic information from RS images. In the second stage, an adaptive feature enhancement (AFE) module computes grayscale information from original images and feature maps produced by the lightweight network and then fuses them to improve the intensity of target edges; a morphological-threshold process (MTP) module automatically generates appropriate initial contours for targets from the semantic feature maps instead of manual contour initialization. Then, a new ACM, proposed based on pre-fitting foreground and background in local regions, uses the statistical characteristics of local intensities and the bias field correction to suppress the interference of non-target regions, thereby improving segmentation accuracy. Experimental results show that the mean Dice Similarity Coefficient (mDSC) and the mean Intersection over Union (mIoU) of our method are higher than those of the suboptimal method by 1.21% and 1.60%, respectively, on average for segmenting images from six RS datasets, which verify the advantage of our proposed method.

Currently, the remote sensing fine-grained rigid object detectors mainly face two challenges: fuzzy localization and inaccurate classification (including misclassifying and multi-classifying). Firstly, mainstream detectors based on the “dense prediction” paradigm suffer from a misalignment between anchor points (APs) and ground truths (GTs). Commonly, they adopt multi-stage regression as a solution, which brings an ambiguous sample definition problem and redundant computational costs. Secondly, two factors seriously affect the classification. They are the insufficient sample learning caused by the long-tail distribution of categories, and the difficulty in extracting discriminative features caused by slight inter-class variance. To address the issues above, we propose an efficient aligning and completing detector (ACDet) based on a single-stage structure. Firstly, the Adaptive Anchor Alignment Mechanism decouples the centripetal sampling bias in the categorical features and leverages it to learn the APs aligned with GTs. It is plug-and-play, requiring no additional supervision annotations. Secondly, a novel Online Tail-sample Supplementation algorithm is proposed. It dynamically maintains class balance during training and can be easily added as post-processing behind existing sample assignment strategies. Thirdly, an Adaptive Group Perceptron is designed to effectively enrich the diversity of features and enhance the model’s ability to extract discriminative features. Experiments on four public datasets demonstrate that the proposed ACDet achieves the state-of-the-art (SOTA) level, even surpassing competitive multi-stage detectors, with fewer computing resources and a faster inference speed. The code will be public after the paper is published.

It is challenging for active contour models (ACMs) to segment weak-edge and noisy images efficiently and accurately. To solve this problem, a novel ACM is proposed in this work. The proposed ACM achieves high-precision segmentation for weak-edge and noisy images using a non-local feature fitting energy function and a scalable normalization method. The non-local feature fitting energy function is constructed based on the distances calculated by Jeffreys divergence between non-local weighted fitting images and the image processed by the non-local means (NLM) algorithm. The non-local weighted fitting images include the fitting foreground and background with image edge features. The images processed by the NLM algorithm is used to reduce the influence of noise. The data-driven term, obtained by minimizing the non-local feature fitting energy function, is computed before the level set iteration, which improves the computation speed. In addition, a scalable normalization method is proposed to normalize the data-driven term. The ability to distinguish the targets from the background for different types of images is enhanced by adjusting a scaling factor, improving the robustness and accuracy of the proposed model. Experimental results demonstrate the advantages of the proposed model.

Methods combining deep neural networks (DNN) and active contour models (ACM) have shown effective performance in building segmentation tasks. However, due to the independent structural design, it suffers from a large amount of parameters and computational cost. To address the above problem and further explore the performance effect of the coupling DNN and ACM methods, we present a Parameter-efficient Differentiable Active Contour (PDAC) network for precisely segmenting buildings in remote sensing scenarios. Specifically, an adapter is applied to fine-tune the encoder, instead of initializing a new one. Based on it, a semantic segmentation model can achieve further localization improvement by introducing a minor amount of parameters. Experiments on two BE datasets show that PDAC achieves better performance with nearly half of the computational resources than the baseline.

The essence of improving the effect of cross-modal image-text retrieval (CIR) lies in the finer-grained modeling of homogeneous features between modalities. However, in remote sensing (RS) scenarios, existing methods usually apply the image-sentence granular feature alignment paradigm, bringing significant difficulties to the fine-grained representation of homogeneous features between modalities. Besides, more complex background noise and extreme scale ranges of foreground targets are hard to distinguish, causing the feature mottle problem. To address the above issues, we propose a novel Semantic-guided Image-text Retrieval framework with Segmentation (SIRS). It is a multi-task joint learning framework for plug-and-play and end-to-end training RS CIR models efficiently, including Semantic-guided Spatial Attention (SSA) and Adaptive Multi-scale Weighting (AMW) modules. First, SSA introduces a background reconstruction branch based on noise perception and a semantic segmentation branch based on pixel-level prediction. It explores a joint learning strategy that concisely filters background noise and refines foreground features considerably. Secondly, AMW performs multi-scale weighting on various layers of feature map output by the encoder, effectively improving the learning efficiency of foreground targets at different scales. It is worth mentioning that SIRS outputs combination results with image and segmentation mask, which is not available in other methods. Based on the RSITMD dataset, we complete the semantic segmentation annotation RSITMD-SS to verify the performance of the proposed method. Sufficient and complete experiments verify the effectiveness of the proposed method. With SIRS, the mainstream SVP and CLIP-based methods improve about 7 mR and derive segmentation prediction with acceptable computational cost optionally. The code and associated dataset will be available on https://github.com/StarBurstStream0/SIRS.

Classical diffusion adaptive filtering algorithms are often designed to deal with unconstrained system identification. However, they are not suited to constrained system identification. This work develops a diffusion constrained adaptive filtering algorithm to address the above problem. We use the cost function based on the half-quadratic criterion (HQC) to enhance the robustness of the nodes against impulsive noise. We also utilize the strategy of data sharing between the neighboring nodes to promote the network convergence performance. To investigate the stochastic behavior, we further analyse the stability condition and the transient and steady-state performance of the proposed diffusion constrained HQC (DCHQC) algorithm under several commonly used statistical assumptions. Simulation results are given to show the advantages of DCHQC in the context of distributed constrained system identification and beamforming and to validate the theoretical expressions on the performance prediction.

In the application of system identification, not only the output but also the input of the system may be corrupted by noise, which is often characterized by the errors-in-variables (EIV) model. To identify such systems, a gradient-descent total least-squares (GD-TLS) and a maximum total correntropy (MTC) algorithms were proposed. In some scenarios, the weight vector of the unknown system may be sparse, e.g., the echo path in acoustic echo cancelation (AEC). Employing TLS or MTC to estimate such systems may result in slow convergence rate, since they assign the same gain to the update of each weight and therefore cannot make use of the sparsity feature of the system to accelerate convergence. To address the above problem, this article proposes a uniform optimization model for deriving proportionate total adaptive filtering algorithms, and then two proportionate total adaptive filtering algorithms are developed, namely, the proportionate total normalized least mean square (PTNLMS) algorithm for Gaussian noise disturbance and the proportionate MTC (PMTC) algorithm for impulsive noise interference, which are both derived by utilizing the method of Lagrange multipliers. Moreover, this article also makes a steady-state performance analysis of the two proposed algorithms. Simulations are performed to demonstrate the superior performance of the two proposed algorithms and to test the accuracy of the theory on the steady-state performance analysis.

Sparse system identification is often encountered in applications such as network and acoustic echo cancellation. This work applies the sparsity promoting method to the affine projection algorithm (APA) to develop a sparsity-promoting APA (SAPA). To reduce its computational complexity, the gain matrix of SAPA is periodically updated, which leads to a periodically updated gain matrix based SAPA (PSAPA). In addition, the steady-state and tracking performance of PSAPA is analyzed using an improved weighted energy conservation method, which takes account of the correlation between the adaptive filter weight vector and the noise vector. The results of performance analysis are also suited to other proportionate APAs (PAPAs). Simulation results verify the advantages of the proposed algorithms and show that the theoretical expressions on the steady-state and tracking performance can predict the stochastic behaviors well.

Most state-of-the-art deep learning-based methods for extraction of building footprints are aimed at designing proper convolutional neural network (CNN) architectures or loss functions able to effectively predict building masks from remote sensing (RS) images. To properly train such CNN models, large-scale and pixel-level building annotations are required. One common approach to obtain scalable benchmark data sets for the segmentation of buildings is to register RS images with auxiliary geospatial information data, such as those available from OpenStreetMaps (OSM). However, due to land-cover changes, urban construction, and delayed geospatial information updating, some building annotations may be missing in the corresponding ground-truth building mask layers. This will likely introduce confusion in the training of CNN models for discriminating between background and building pixels. To solve this important issue, we first formulate the problem as a long-tailed classification one. Then, we introduce a new joint loss function based on three terms: 1) logit adjusted cross entropy (LACE) loss, aimed at discriminating between building and background pixels from a long-tailed label distribution; 2) weighted dice loss, aimed at increasing the$F_{1}$scores of the predicted building masks; and 3) boundary (BD) alignment loss, which is optimized for preserving the fine-grained structure of building boundaries. Our experiments, conducted on two benchmark building segmentation data sets, validate the effectiveness of our newly proposed loss with respect to other state-of-the-art losses commonly used for extracting building footprints. The codes of this letter will be publicly available fromhttps://github.com/jiankang1991/GRSL_BFE_MA.

When the noise is second-order (SO) noncircular, the least stochastic entropy (LSE) algorithm can obtain a low steady-state misalignment compared to the complex-valued least mean-square (CLMS) algorithm. However, the convergence rate of LSE will decrease if the input of the adaptive filter is SO noncircular. This letter analyzes the cause of this problem and proposes an improved LSE (ILSE), which uses a combination strategy to accelerate its convergence rate. To predict its stochastic behavior, the performance of ILSE is analyzed. Simulation results are provided to verify the effectiveness of ILSE and the accuracy of the theoretical analysis.

Endowing convolutional neural networks (CNNs) with the rotation-invariant capability is important for characterizing the semantic contents of remote sensing (RS) images since they do not have typical orientations. Most of the existing deep methods for learning rotation-invariant CNN models are based on the design of proper convolutional or pooling layers, which aims at predicting the correct category labels of the rotated RS images equivalently. However, a few works have focused on learning rotation-invariant embeddings in the framework of deep metric learning for modeling the fine-grained semantic relationships among RS images in the embedding space. To fill this gap, we first propose a rule that the deep embeddings of rotated images should be closer to each other than those of any other images (including the images belonging to the same class). Then, we propose to maximize the joint probability of the leave-one-out image classification and rotational image identification. With the assumption of independence, such optimization leads to the minimization of a novel loss function composed of two terms: 1) a class-discrimination term and 2) a rotation-invariant term. Furthermore, we introduce a penalty parameter that balances these two terms and further propose a final loss to Rotation-invariant Deep embedding for RS images, termed RiDe. Extensive experiments conducted on two benchmark RS datasets validate the effectiveness of the proposed approach and demonstrate its superior performance when compared to other state-of-the-art methods. The codes of this article will be publicly available athttps://github.com/jiankang1991/TGRS_RiDe.

The diffusion subband adaptive filtering algorithm has faster convergence rate than the diffusion least mean square algorithm. In the case where the measurement noise includes impulsive interferences, however, this algorithm may suffer from bad convergence performance. This letter proposes a diffusion sign subband adaptive filtering algorithm, which is derived based on the method of minimization of the l1-norm of the intermediate subband a posteriori error vector subject to a constraint on the intermediate estimate of the unknown vector at each agent in the network. Simulation results demonstrate that the proposed algorithm is robust against impulsive interferences.

-norm optimization-based sign algorithms (SAs) are more robust against impulsive interference than -norm optimization-based adaptive filtering algorithms. However, most SAs suffer from slow convergence rate, especially for highly correlated input signals. In order to overcome this problem, recently, an affine projection SA (APSA) has been proposed , which exhibits fast convergence rate. In this letter, we first analyze the computational complexity of the APSA in detail and then apply a recursive approach proposed for the affine projection algorithm (APA) to the APSA to reduce its computational complexity. Analysis results show that the computational complexity of the APSA with the efficient implementation method is even lower than that of the classical fast affine projection (FAP) algorithm.

The normalized subband adaptive filter (NSAF) presented by Lee and Gan can obtain faster convergence rate than the normalized least-mean-square (NLMS) algorithm with colored input signals. However, similar to other fixed step-size adaptive filtering algorithms, the NSAF requires a tradeoff between fast convergence rate and low misadjustment. Recently, a set-membership NSAF (SM-NSAF) has been developed to address this problem. Nevertheless, in order to determine the error bound of the SM-NSAF, the power of the system noise should be known. In this paper, we propose a variable step-size matrix NSAF (VSSM-NSAF) from another point of view, i.e., recovering the powers of the subband system noises from those of the subband error signals of the adaptive filter, to further improve the performance of the NSAF. The VSSM-NSAF uses an effective system noise power estimate method, which can also be applied to the under-modeling scenario, and therefore need not know the powers of the subband system noises in advance. Besides, the steady-state mean-square behavior of the proposed algorithm is analyzed, which theoretically proves that the VSSM-NSAF can obtain a low misadjustment. Simulation results show good performance of the new algorithm as compared to other members of the NSAF family.

The normalized subband adaptive filter (NSAF) proposed by Lee and Gan is promising. However, there exists the conflicting requirement of fast convergence rate and low misadjustment for the NSAF. In this letter, we propose a variable regularization matrix NSAF (VRM-NSAF) to address this problem. The optimal selection of the regularization matrix is derived by the largest decrease of the mean-square deviation (MSD). Simulation results comparing the proposed VRM-NSAF with the original NSAF are presented to show the advantage of this method, including both fast convergence rate and low misadjustment.