Scene-aware Adaptive Compressive Sensing (ACS) has attracted significant interest due to its promising capability for efficient and high-fidelity acquisition of scene images. ACS typically prescribes adaptive sampling allocation (ASA) based on previous samples in the absence of ground truth. However, when confronting unknown scenes, existing ACS methods often lack accurate judgment and robust feedback mechanisms for ASA, thus limiting the high-fidelity sensing of the scene. In this paper, we introduce a Sampling Innovation-Based ACS (SIB-ACS) method that can effectively identify and allocate sampling to challenging image reconstruction areas, culminating in high-fidelity image reconstruction. An innovation criterion is proposed to judge ASA by predicting the decrease in image reconstruction error attributable to sampling increments, thereby directing more samples towards regions where the reconstruction error diminishes significantly. A sampling innovation-guided multi-stage adaptive sampling (AS) framework is proposed, which iteratively refines the ASA through a multistage feedback process. For image reconstruction, we propose a Principal Component Compressed Domain Network (PCCD-Net), which efficiently and faithfully reconstructs images under AS scenarios. Extensive experiments demonstrate that the proposed SIB-ACS method significantly outperforms the state-of-the-art methods in terms of image reconstruction fidelity and visual effects. Codes are available at https://github.com/giant-pandada/SIBACS_CVPR2025.

Abstract This paper presents a new algorithm named combination search strategy (CSS)‐based improved particle swarm optimisation (IPSO) to address the resource allocation problem of multiple jammers. First, the authors propose a CSS to effectively broaden the limited search range of the two‐step solving framework. This method not only simplifies the solution framework but also considers the combined relationship between beam pointing and transmit power to determine the global solution to the original problem directly. Second, the authors propose the IPSO because the complexity of the decision variables is increased by CSS. This method can change the focus of searching the optimal solution at different stages, correct the direction of particle evolution over time and avoid the interference between the variables. Finally, this study simulates the problem of resource allocation of multiple jammers based on the CSS‐IPSO. Based on the simulation results, the combined search strategy can obtain better resource allocation results in a short time, and the IPSO algorithm can further improve the accuracy and stability of the resource allocation results.

Change detection in synthetic aperture radar (SAR) images has garnered significant research interest. However, to date, only the change area can be obtained, which seriously restricts further development of SAR image applications. To solve this problem, this paper proposes a change type recognition method for SAR images based on a statistical bidirectional long short-term memory (LSTM) network. The proposed method can obtain the changed area and identify the land type change between pairs of SAR images. Considering the statistical characteristics and sample number of SAR images, change detection and type recognition are realized in a unified framework. First, feature extraction is performed through the statistical features of the original SAR image and difference image (DI). Then, a bidirectional LSTM network is used to identify the change types and obtain the change detection results under the small sample deep learning network. On two sets of medium-low resolution SAR image data and one set of GaoFen-3 high-resolution real SAR image data, our method produced high-quality results under small sample conditions.

In order to evaluate quantitatively the preservation performance of polarimetric information for polarimetric synthetic aperture radar (PolSAR) speckle filters, this letter presents correlation coefficients between the original and the filtered polarimetric data based on the theory of polarization synthesis. The copolarized and the cross-polarized correlation coefficients are furthermore discussed in cases whether the transmitting and receiving radar antennas are characterized by the same or orthogonal polarization state. To show how these coefficients can be exploited in evaluating the preservation of polarimetric information, they are demonstrated with a German Aerospace Center (DLR) Experimental Synthetic Aperture Radar L-band full-polarized image of the Oberpfaffenhofen Test Site Area (DE), Germany, which was obtained on September 30, 2000. Results make evident that the correlation coefficients are efficient to describe quantitatively the performance in preserving polarimetric information for PolSAR speckle filters.