DNOD: Deformable Neural Operators for Object Detection in SAR Images

GVS Mothish, J Rishi, Shobhit Kumar Shukla, Deepak Subramani

Abstract: We introduce a deep neural operator framework aimed at object detection in remotely sensed Synthetic Aperture Radar (SAR) images. Recent research highlights the impressive performance of the End-to-End Object Detection Transformer (DETR). Nonetheless, in domains like SAR imaging, managing challenges such as speckle noise and the detection of small objects continues to be problematic. To address SAR object detection issues, we present the Deformable Neural Operator-Based Object Detection (DNOD) framework, tailored for SAR tasks. We develop two neural operators: Multi-Scale Fourier Mixing (MSFM) for the encoder and Multi-scale, multi-input Adaptive Deformable Fourier Neural Operator (MADFNO) for the decoder. Detailed evaluations and ablation studies show that DNOD exceeds existing methods, delivering significantly better results with an improvement of +2.23 mAP on the SARDet-100k dataset, the largest SAR object detection compilation. The code is available at https://github.com/quest-lab-iisc/DNOD.

Certifications: J2C Certification

Submission Length: Regular submission (no more than 12 pages of main content)

Code: https://github.com/quest-lab-iisc/DNOD

Assigned Action Editor: ~Yin_Cui1

Submission Number: 5165