arXiv:2610.27883v1 Announce Type: new Abstract: Multispectral aerial object detection aims to exploit spectral-spatial cues to address object detection challenges in complex aerial scenes. Existing m...
Multispectral aerial object detection aims to exploit spectral-spatial cues to address object detection challenges in complex aerial scenes. Existing methods mainly focus on spectral-spatial decouplin...
RoES is a Rotational Equivariant Selective-frequency fusion network that dynamically separates low- and high-frequency components of infrared-visible images. It uses a trainable rotation-enhanced updater to decouple frequencies, then fuses them with a dual-branch module: a rotation-equivariant Mamba for low-frequency structural dependencies and a polar spectral attention Dual-Fourier block for high-frequency detail refinement. Experiments show RoES outperforms existing methods in fusion quality and downstream object detection, offering a robust multimodal fusion solution.
FoCal is a new frequency‑oriented framework for aerial RGB–IR object detection that explicitly models cross‑modal interaction across different frequency components. It introduces a Frequency‑Aware Dual‑Domain Calibration module to consolidate low‑frequency structural cues while preserving high‑frequency modality‑specific details, and a Discrepancy‑Guided Spectral Modulation module that adaptively enhances, preserves, or attenuates the joint spectrum based on confidence‑weighted amplitude discrepancies. Experiments on DroneVehicle, ESCVehicle, and ATR‑UMOD show FoCal achieving high mAP scores (83.5%, 54.8%, 64.6%) with only 3.0 M parameters and 113.6 FPS, demonstrating a strong accuracy–efficiency trade‑off.
arXiv:2512.15971v2 Announce Type: replace Abstract: Multispectral object detection is critical for safety-sensitive applications such as autonomous driving and surveillance, where robust perception u...
arXiv:2608.30355v1 Announce Type: new Abstract: Recent advances in camouflaged object detection (COD) have led to substantial progress in challenging low-visibility scenarios, with pioneering studies...
LESSViT introduces a sensor‑flexible Vision Transformer for hyperspectral imagery that uses a low‑rank structured attention mechanism (LESS Attention) to efficiently model joint spatial‑spectral interactions. By reducing the complexity from ≠O(N^2C^2) to ≠O(rNC) and adding channel‑agnostic patch embedding with wavelength‑aware positional encoding, it supports flexible spectral inputs. A hyperspectral masked autoencoder (HyperMAE) with decoupled spatial‑spectral masking further enables robust pretraining, and experiments on the SpectralEarth benchmark show improved robustness to spectral shifts while maintaining competitive in‑distribution performance.
AGSA-Net is a hyperspectral image classification framework that incorporates spectral unmixing priors through an abundance-guided self‑attention network. It first estimates physically meaningful subpixel abundance maps with non‑negativity and sum‑to‑one constraints, then uses these abundances to build an affinity prior that directs a spectral transformer to focus on class‑discriminative interactions. The transformer features are fused with compact abundance descriptors for final classification, and experiments on Indian Pines, Augsburg, and Berlin datasets show improved performance, especially in heterogeneous urban scenes.
Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs, Vision Transformers, Mamba, graph neural networks, Kolmogorov Arnold networks, and se...
arXiv:2606. 10819v1 Announce Type: cross Abstract: RS-MLLMs enable natural-language understanding and spatial reasoning over earth observation imagery.
arXiv:2608.27971v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV) multimodal perception integrates visible (RGB), infrared (IR), synthetic aperture radar (SAR), and depth sensors for scen...
Vision Foundation Models (VFMs) have significantly advanced dense feature matching, yet severe in-plane rotation remains a critical challenge. Existing solutions face a fundamental dilemma: data-driven methods require inefficient parameter scaling to implicitly learn rotations, whereas strictly equivariant networks lack the semantic capacity of modern VFMs.