Change detection (CD) of remotely sensed (RS) images is mushrooming up accompanied by the on-going innovation of convolutional neural networks (CNNs). Yet with the high-speed technology upgrade, the obstacle that identifies unbalanced variations of foreground-background categories still lies on the table, especially in cases with limited samples and massive interference such as seasonal turnover, illumination intensity, and building reformation. Moreover, to date, neither of the off-the-shelf methods probes the feasibility of direct interaction between bi-temporal images before accessing difference features. In this paper, we propose a dual-branch multi-level inter-temporal network (DMINet) to efficiently and effectively derive the change representations. Specifically, by unifying self-attention and cross-attention in a single module, we present an inter-temporal joint-attention block to steer the global feature distribution of each input, motivating information coupling between intra-level representations and meanwhile suppressing the task-irrelevant interferences. In addition, centering more on the detection of difference features, a reliable architecture is designed by spotlighting two concerns, i.e., the difference acquisition using subtraction and concatenation, as well as the multi-level difference aggregation using incremental feature alignment. Based on a naive backbone without sophisticated structures, i.e., ResNet18, our model outperforms other state-of-the-art methods on four CD datasets, especially in cases with rarely samples. Moreover, the achievement is attained with light overheads.

Change detection (CD) of remote sensing (RS) images has enjoyed remarkable success by virtue of convolutional neural networks (CNNs) with promising discriminative capabilities. However, CNNs lack the capability of modeling long-range dependencies in bitemporal image pairs, resulting in inferior identifiability against the same semantic targets yet with varying features. The recently thriving Transformer, on the contrary, is warranted, for practice, with global receptive fields. To jointly harvest the local-global features and circumvent the misalignment issues caused by step-by-step downsampling operations in traditional backbone networks, we propose an intra-scale cross-interaction and inter-scale feature fusion network (ICIF-Net), explicitly tapping the potential of integrating CNN and Transformer. In particular, the local features and global features, respectively, extracted by CNN and Transformer, are interactively communicated at the same spatial resolution using a linearized Conv Attention module, which motivates the counterpart to glimpse the representation of another branch while preserving its own features. In addition, with the introduction of two attention-based inter-scale fusion schemes, including mask-based aggregation and spatial alignment (SA), information integration is enforced at different resolutions. Finally, the integrated features are fed into a conventional change prediction head to generate the output. Extensive experiments conducted on four CD datasets of bitemporal (RS) images demonstrate that our ICIF-Net surpasses the other state-of-the-art (SOTA) approaches.

Fusion from a spatially low resolution hyperspectral image (LR-HSI) and a spectrally low resolution multispectral image (MSI) to produce a high spatial-spectral HSI (HR-HSI), known as hyperspectral super resolution, has risen to a preferred topic for reinforcing the spatial-spectral resolution of HSI in recent years. In this work, we propose a new model, namely, low-rank tensor ring decomposition based on tensor nuclear norm (LRTRTNN), for HSI-MSI fusion. Specifically, for each spectrally subspace cube, similar patches are grouped to exploit both the global low-rank property of LR-HSI and the nonlocal similarity of HR-MSI. Afterward, a joint optimization of all groups via the presented LRTRTNN approximation is implemented in a unified cost function. With the introduced tensor nuclear norm (TNN) constraint, all 3D tensor ring factors are no longer unfolded to suit the matrix nuclear norm used in conventional methods, and the internal tensor structure can be naturally retained. The alternating direction method of multipliers is introduced for coefficients update. Numerical and visual experiments on real data show that our LRTRTNN method outperforms most state-of-the-art algorithms in terms of fusing performance.

With the prosperity of deep learning techniques, salient object detection in remote sensing images (RSI-SOD) is concomitantly in full flourishing. However, due to the inherent challenges such as uncertainty in object quantities and scales, cluttered backgrounds, and blurred edges arising from shadows, most current approaches struggle for salient feature learning with the aid of heavy model architecture, yet often result in barely satisfactory performance. Some methods compromise model complexity to improve efficiency, albeit with significantly degraded results. To earn a satisfactory balance of efficacy and efficiency, we propose a new network for RSI-SOD, namely SFANet, based on progressive semantic flow and uncertainty-aware refinement. Specifically, we design a global semantic enhancement block (GSEB) to reduce background interference and accurately localize salient objects of varying quantities and scales, which further consists of three modularized components, i.e., semantic extraction module (SEM), interscale fusion module (IFM), and deep semantic graph-inference module (DSGM). SEM together with IFM contributes to the effective aggregation of multi-scale contexts by extracting fused and progressive semantic cues. DSGM performs semantic inference to better localize salient objects with irregularities in scale and topological structure. Furthermore, we present an uncertainty-aware refinement module (URM) to recognize salient objects in cluttered backgrounds and effectively suppress shadows. Extensive experiments are conducted on three RSI-SOD datasets, from which superior results can be achieved by our SFANet, outperforming the other cutting-edge methods. The code is available at https://github.com/ZhengJianwei2/SFANet.

Low-rank modeling has achieved great success in visual data completion. However, the low-rank assumption of original visual data may be in approximate mode, which leads to suboptimality for the recovery of underlying details, especially when the missing rate is extremely high. In this paper, we go further by providing a detailed analysis about the rank distributions in Hankel structured and clustered cases, and figure out both non-local similarity and patch-based structuralization play a positive role. This motivates us to develop a new Hankel low-rank tensor recovery method that is competent to truthfully capture the underlying details with sacrifice of slightly more computational burden. First, benefiting from the correlation of different spectral bands and the smoothness of local spatial neighborhood, we divide the visual data into overlapping 3D patches and group the similar ones into individual clusters exploring the non-local similarity. Second, the 3D patches are individually mapped to the structured Hankel tensors for better revealing low-rank property of the image. Finally, we solve the tensor completion model via the well-known alternating direction method of multiplier (ADMM) optimization algorithm. Due to the fact that size expansion happens inevitably in Hankelization operation, we further propose a fast randomized skinny tensor singular value decomposition (rst-SVD) to accelerate the per-iteration running efficiency. Extensive experimental results on real world datasets verify the superiority of our method compared to the state-of-the-art visual inpainting approaches.

The application of optical remote sensing images (ORSIs) is prevalent in many fields. Accordingly, ORSI-oriented saliency object detection (SOD) has attracted more attention in recent years. However, yet many previously proposed methods present appealing performance in natural scene images (NSIs), they are difficult to be directly extended to remote sensing images due to the more complex scenes, such as blended backgrounds and diversiform topological shapes. Most specifically designed models often fail to achieve satisfactory results due to the weak usage of edge information and the ignorance of attention loss. Besides, computational inefficiency often causes poor applicability. To solve these problems, we propose a new model, namely Bidimensional Attention and Full-stage Semantic Guidance Network (BAFS-Net), containing an edge guidance branch and a mainstream detection branch. Concretely, edge guidance generates boundary information, in which a supervision with border labels is imposed to highlight the salient regions and plays a complementary role on the main branch. The mainstream detection branch involves two important components, i.e. bidimensional attention modules (BAM) and semantic-guided fusion modules (SGFM). Between these two, BAM uniformly assembles channel and spatial attention in an efficient and rational manner, addressing the open issue of dimension-wisely attention computation. SGFM hammers at the fusion of high-level features and low-level features. Moreover, the semantic maps are employed to interact with SGFM in full stages. Our approach surpasses most state-of-the-art RSIs-SOD methods proposed in recent years, with respect to accuracy, parameter size, computational cost, and FLOPS, as shown in Fig. 1. Code is available at https://github.com/ZhengJianwei2/BAFS-Net.