20 February 2024 in IEEE Transactions on Geoscience and Remote Sensing
High-resolution remote sensing image change detection focuses on ground surface changes. It has wide applications, including territorial spatial planning, urban region detection, and military operations. However, class imbalance and pseudo-changes are caused by the unchanged areas far outnumbering the changed areas and lighting changes. To address these problems, we propose spatial-temporal attention with a difference enhancement-based network (STADE-CDNet). In STADE-CDNet, a change detection difference enhancement module (CDDM) is proposed to extract important features from the difference map to detect changed regions. This module enhances the network with differential feature attributes through the training layer, improving the network’s learning ability and reducing the imbalance problem. A temporal memory module (TMM) is designed to extract temporal and spatial information. Inspired by the self-attention mechanism of the transformer, we propose a transformer and TMM (TTMM). Four encoding layers are designed to detect the semantic information from high to low levels of the multitemporal image pairs. The fusion and parallelism of multivariate data are achieved through collaborative modeling of deep learning and change detection, compensating for the need for excessive human intervention in traditional algorithms. We evaluate our approach in two different datasets (LEVIR-CD and DSIFN-CD). Promising quantitative and qualitative results show that STADE-CDNet can improve accuracy. In particular, the proposed CDDM significantly reduces false positive detection, with F1 scores at least 1.97% and 2.1% higher than other methods in the case of the LEVIR-CD and DSIFN-CD datasets, respectively. Our code is available at https://github.com/LiLisaZhi/STADE-CDNet.
20 June 2023 in IEEE Transactions on Geoscience and Remote Sensing
Infrared small target detection (ISTD) is vital for civil and military applications. However, existing methods often face challenges in coping with complex scenes, discriminating targets from similar objects, or leveraging temporal information effectively. To tackle these limitations, we offer an innovative approach that exploits the spatio-temporal structure of infrared images. A four-dimensional (4D) infrared tensor is initially constructed from a sequence of infrared images, and decomposed into lower-dimensional tensors using the tensor train (TT) and its extension – tensor ring (TR) techniques. The ISTD problem is then formulated as a sparse plus low-rank decomposition problem, where the sparse part is the target and the low-rank part is the background. We factorize the composed tensors into matrices via TT and TR unfolding approaches, which mitigates the imbalance between different modes containing spatial and temporal information. By constraining the balanced unfolded components with the weighted sum of nuclear norm, we solve the problem using the alternating direction multiplier method (ADMM). Furthermore, we validate models on several datasets and benchmark them with state-of-the-art techniques in detection accuracy and background suppression. Comparison results demonstrate the superiority of our approach over the existing methods. Moreover, the results of an ablation study with three-dimensional (3D) tensor structures show the effectiveness and feasibility of the dimension expansion to 4D.
24 December 2024 in IEEE Transactions on Geoscience and Remote Sensing
Infrared small target detection (ISTD) boasts extensive applications across civil and military domains, owing to its exceptional all-day performance. Neural network innovations have led to deep ISTD models that achieve heightened accuracy through extensive datasets. However, these general networks often fail to perceive the sensitivity of small targets and adopt heavy constructions to preserve potential target features, neglecting domain-specific insights and suffering from poor explainability. Our work seeks to rectify this by revisiting the saliency principles inherent to ISTD and developing a Learnable Local Saliency Kernel Network (L 2 SKNet). This approach implements a learnable local saliency kernel module (LLSKM) that embodies the concept of "Center subtracts Neighbors", guiding the network to capture the saliency features (points or edges). We enhance LLSKM by incorporating strategic dilation and structuring it hierarchically, which boosts its capability to capture multi-scale infrared features while avoiding parameter explosion. In pursuit of efficiency, we also refine LLSKM into a more compact form by factorizing it into two orthogonal 1-D kernels, yielding a lightweight version. Heatmap visualizations and rigorous quantitative analyses corroborate the effectiveness of our local saliency-guided networks. Comprehensive testing reveals that L 2 SKNet variants outperform established baselines, demonstrating significant improvements in both visual and numerical assessments. The code is available at https://github.com/fengyiwu98/L2SKNet.
6 May 2022 in Molecular Pain
The anterior cingulate cortex (ACC) is a key cortical region that plays an important role in pain perception and emotional functions. Previous studies of the ACC projections have been collected primarily from monkeys, rabbits and rats. Due to technological advances, such as gene manipulation, recent progress has been made in our understanding of the molecular and cellular mechanisms of the ACC-related chronic pain and emotion is mainly obtained from adult mice. Few anatomic studies have examined the whole-brain projections of the ACC in adult mice. In the present study, we examined the continuous axonal outputs of the ACC in the whole brain of adult male mice. We used the virus anterograde tracing technique and an ultrahigh-speed imaging method of Volumetric Imaging with Synchronized on-the-fly-scan and Readout (VISoR). We created a three-dimensional (3D) reconstruction of mouse brains. We found that the ACC projected ipsilaterally primarily to the caudate putamen (CPu), ventral thalamic nucleus, zona incerta (ZI), periaqueductal gray (PAG), superior colliculus (SC), interpolar spinal trigeminal nucleus (Sp5I), and dorsal medullary reticular nucleus (MdD). The ACC also projected to contralateral brain regions, including the ACC, reuniens thalamic nucleus (Re), PAG, Sp5I, and MdD. Our results provide a whole-brain mapping of efferent projections from the ACC in adult male mice, and these findings are critical for future studies of the molecular and synaptic mechanisms of the ACC and its related network in mouse models of brain diseases.
14 July 2025 in IEEE Transactions on Geoscience and Remote Sensing
Infrared small target detection plays a vital role in remote sensing, industrial monitoring, and various civilian applications. Despite recent progress powered by deep learning, many end-to-end convolutional models tend to pursue performance by stacking increasingly complex architectures, often at the expense of interpretability, parameter efficiency, and generalization. These models typically overlook the intrinsic sparsity prior of infrared small targets–an essential cue that can be explicitly modeled for both performance and efficiency gains. To address this, we revisit the model-based paradigm of Robust Principal Component Analysis (RPCA) and propose Dynamic RPCA Network (DRPCA-Net), a novel deep unfolding network that integrates the sparsity-aware prior into a learnable architecture. Unlike conventional deep unfolding methods that rely on static, globally learned parameters, DRPCA-Net introduces a dynamic unfolding mechanism via a lightweight hypernetwork. This design enables the model to adaptively generate iteration-wise parameters conditioned on the input scene, thereby enhancing its robustness and generalization across diverse backgrounds. Furthermore, we design a Dynamic Residual Group (DRG) module to better capture contextual variations within the background, leading to more accurate low-rank estimation and improved separation of small targets. Extensive experiments on multiple public infrared datasets demonstrate that DRPCA-Net significantly outperforms existing state-of-the-art methods in detection accuracy. Code is available at https://github.com/GrokCV/DRPCA-Net.
28 November 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Infrared small target detection (ISTD) technology has extensive applications in the military field. Due to the quality of imaging equipment and environmental interference, infrared small target images lack texture and structural information. Deep learning-based algorithms have achieved superior accuracy in this field compared to traditional algorithms; however, these methods are often not designed with domain knowledge integration. In this article, we propose a multidirectional information-guided contextual network (MDIGCNet) for ISTD. The primary structure of this network adopts the U-Net architecture. To address the issue of lacking texture and structural information in the target images, we employ an integrated differential convolution (IDConv) module to extract richer image features during both the encoding and decoding stages. Skip connections in the network utilize a multidirectional gradient information extraction block (MGIEB) to obtain gradient features of infrared small targets. Our domain-inspired multidirectional Gaussian differential convolution (MGDC) module is employed to extract features of Gaussian-distributed small targets, enhancing the distinction between targets and backgrounds. Additionally, we designed a local-global feature fusion (LGFF) module incorporating an attention mechanism to merge shallow and deep features, thereby improving the efficiency of feature utilization within the model. Furthermore, since both IDConv and MGDC are parallel multiconvolutional kernel structures, reparameterization techniques are used to avoid excessive parameters and computational load. Experimental results on public datasets NUDT-SIRST, IRSTD-1k, and SIRST-Aug demonstrate that our algorithm outperforms other state-of-the-art methods in detection performance.