A Zero-Shot NAS Method for SAR Ship Detection Under Polynomial Search Complexity

One-shot neural architecture search (NAS) has achieved impressive results in the field of synthetic aperture radar (SAR) ship detection. However, it is a challenge to balance resource consumption and search speed. To address this issue, we propose a zero-shot NAS method for searching the backbone of SAR ship detection model, named as ZeroSARNas, which is implemented via a multi-characterization proxy and an integer linear programming (ILP) search algorithm. Specifically, we first design the multi-characterization proxy for network capacity prediction, which takes advantage of information entropy and local intrinsic dimensionality (LID) of feature maps, named as ELID proxy, to obtain a more comprehensive understanding of each candidate module in the search space. We then formulate the NAS problem as a '0-1' ILP problem which maximizes the ELID value under the different constraints such as parameters to quickly identify the optimal network. The experimental results show that the detection accuracy of the networks found by ZeroSARNas on the SSDD, HRSID, and LS-SSDD-v1.0 datasets can reach 98.59%, 91.30%, and 75.11% in mean average precision (mAP) with only 1.23 M, 1.75 M, and 1.29 M parameters, respectively. The proposed method reduces the search time from several GPU days or hours to 10.0 seconds, achieving competitive search efficiency.