AI RESEARCH
PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection
arXiv CS.CV
•
ArXi:2603.16341v1 Announce Type: new Object detection in remote sensing images (RSIs) is challenged by the coexistence of geometric and spatial complexity: targets may appear with diverse aspect ratios, while spanning a wide range of object sizes under varied contexts. Existing RSI backbones address the two challenges separately, either by adopting anisotropic strip kernels to model slender targets or by using isotropic large kernels to capture broader context.