SAR-FAH is a Frequency‑Adaptive Hybrid network that uses Neural Ordinary Differential Equations (NODEs) to despeckle Synthetic Aperture Radar (SAR) images. It separates homogeneous and heterogeneous regions in the frequency domain via wavelet transform, then applies a NODE‑based module to low‑frequency sub‑bands for smooth denoising and an enhanced U‑Net with deformable convolutions to high‑frequency sub‑bands for edge and texture preservation. Experiments on synthetic and real SAR data show that SAR‑FAH outperforms current state‑of‑the‑art despeckling methods both quantitatively and qualitatively.
By Ziqing Ma, Chang Yang, Zhichang Guo, Yao Li
arXiv:2512.01782v4 Announce Type: replace-cross
Abstract: Randomized Smoothing (RS) is a prominent technique for certifying the robustness of neural networks against adversarial perturbations. With R...
By Chenhao Sun, Yuhao Mao, Martin Vechev
The paper introduces a lightweight hierarchical model for environmental sound recognition that combines a Frequency-Time Adaptive Network (FTANet) with a two-stage classification process. FTANet uses parallel asymmetric 1‑D convolutions and adaptive fusion attention to extract temporal and frequency‑band features, first classifying sounds into five coarse categories and then routing them to fine‑grained classifiers. The model achieves high accuracy on a self‑constructed dataset, UrbanSound8K, and real‑world field tests, demonstrating its effectiveness for urban noise monitoring.
By Zhouwen Li, Haijun Lin, Bowen Lv, Yupeng Chen
The paper introduces a sigmoid label for deep‑learning based direction‑of‑arrival (DOA) estimation, encoding DOAs as sums of angle‑shifted monotonic sigmoid functions. Using a CNN‑Transformer network trained with this label, the authors achieve sub‑degree accuracy and 1‑degree resolution with a 0.25° grid step, surpassing traditional Gaussian, hard, and BCE labels. Numerical results confirm the sigmoid label’s superior accuracy and resolution over other labeling approaches.
By Lifeng Wang, Xintong Li, Aifei Liu
arXiv:2606. 28226v1 Announce Type: cross Abstract: Flow Matching (FM) has achieved remarkable generative performance, yet it suffers from exposure bias due to discrepancies between training and inference.
By Guanbo Huang, Jingjia Mao, Fanding Huang, Fengkai Liu, Xiangyang Luo, Yaoyuan Liang, Jiasheng Lu, Xiaoe Wang, Pei Liu, Ruiliu Fu, Ruqi Huang, Shao-Lun Huang
The paper introduces a spatial-frequency-aware implicit neural representation that fuses a Multi‑Layer Perceptron (MLP) branch with a Kolmogorov‑Arnold network (KAN) branch. The MLP captures low‑frequency, smooth structures while the KAN captures high‑frequency, localized details, and their outputs are combined using discrete wavelet transform (DWT) and inverse DWT. A wavelet‑domain band‑separation regularization encourages complementary frequency behavior, and experiments on 1D–4D signals show improved reconstruction fidelity.
By Wen Yan, Ligen Shi, Jun Qiu, Haimiao Zhang, Lina Wu, Chang Liu
arXiv:2511.11286v4 Announce Type: replace-cross
Abstract: Out-of-domain (OOD) robustness is challenging to achieve in real-world computer vision, especially in unsupervised domain adaptation scenario...
By Ruoqi Wang, Haitao Wang, Shaojie Guo, Qiong Luo
arXiv:2609.22139v1 Announce Type: cross
Abstract: Automatic modulation classification (AMC) of received radio signals is prudent for further signal processing tasks such as communication monitoring,...
By Qamar Ijaz, Nayyer Aafaq
Existing object detection methods predominantly utilize sRGB inputs, which are compressed from RAW sensor data using Image Signal Processors (ISP) originally designed for visualization purposes. Compared to RGB images, RAW images possess favorable noise characteristics and richer information representation, which are crucial for object detection, particularly under challenging conditions such as adverse weather or low-light environments.
arXiv:2510.03245v3 Announce Type: replace-cross
Abstract: State-of-the-art attribution methods such as AttEXplore rely on adversarial sample generation that applies an all-pass filter across the freq...
By Ali Yavari, Alireza Mohamadi, Elham Beydaghi, Philipp Seeb\"ock, Rainer A. Leitgeb
arXiv:2610.29108v1 Announce Type: new
Abstract: Blind all-in-one image restoration must adapt a shared model to heterogeneous and sometimes mixed degradations without a task label at test time. We in...
By Trong Nhan Nguyen, Vu Hoang Minh Doan, Thanh Dat Le, Truong Tien Vo, Thi Thu Ha Vu, Tan Hung Vo, Jaeyeop Choi, Junghwan Oh, Truong-Son Hy
The paper presents an AI‑enhanced method for radio frequency interference suppression that builds on autoregressive transformer models by adding a Finite Scalar Quantization tokenizer layer. This addition improves interference rejection while maintaining low latency, and the authors also test other inference optimizations to speed up processing with minimal accuracy loss. Experiments using a digitally modulated RF signal as the signal of interest and a digital television OFDM signal as interference show that the approach outperforms traditional techniques and prior AI methods, with benefits demonstrated through audio quality metrics like PESQ and potential operational applications.
By Rahul Jain, Pierre Trepagnier, Rick Gentile, Joey Botero, Alexia Schulz