Mingzhe Zhu

Xuran Hu, Mingzhe Zhu, Zhenpeng Feng et al.

The inherent "black box" nature of deep neural networks (DNNs) compromises their transparency and reliability. Recently, explainable AI (XAI) has garnered increasing attention from researchers. Several perturbation-based interpretations have emerged. However, these methods often fail to adequately consider feature dependencies. To solve this problem, we introduce a perturbation-based interpretation guided by feature coalitions, which leverages deep information of network to extract correlated features. Then, we proposed a carefully-designed consistency loss to guide network interpretation. Both quantitative and qualitative experiments are conducted to validate the effectiveness of our proposed method. Code is available at github.com/Teriri1999/Perturebation-on-Feature-Coalition.

Xuran Hu, Mingzhe Zhu, Djordje Stanković et al.

Synthetic Aperture Radar (SAR) imagery are widely utilized in remote sensing due to their all-weather, all-day imaging capabilities. However, SAR images are highly susceptible to noise, particularly speckle noise, caused by the coherent imaging process, which severely degrades image quality. This has driven increasing research interest in SAR despeckling. Sparse representation-based methods have been extensively applied in natural image processing, yet SAR despeckling requires addressing non-Gaussian assumption and ensuring sparsity in the transform domain. In this work, we propose a simple, intuitive, and efficient SAR despeckling approach grounded in compressive sensing theory. By applying Log-Yeo-Johnson transformation, we convert gamma-distributed noise into an approximate Gaussian distribution to noise sparse assumption. The method incorporates noise and sparsity priors, leveraging a non-local sparse representation through auxiliary matrices: one capturing varying noise characteristics across regions and the other encoding adaptive sparsity information. Extensive experiments validate the effectiveness of our method.