LiM-YOLO: Less is More with Pyramid Level Shift and Normalized Auxiliary Branch for Ship Detection in Optical Remote Sensing Imagery
This work solves the problem of detecting ships in optical remote sensing imagery for applications like maritime surveillance, but it is incremental as it builds on existing YOLO architectures.
The paper tackled ship detection in satellite imagery by proposing LiM-YOLO, which reconfigures detection heads and adds normalization to address scale disparities, achieving superior accuracy and efficiency on multiple benchmarks.
Applying general-purpose object detectors to ship detection in satellite imagery presents significant challenges due to the extreme scale disparity and morphological anisotropy of maritime targets. Standard architectures utilizing stride-32 (P5) layers often fail to resolve narrow vessels, resulting in spatial feature dilution. In this work, we propose LiM-YOLO, a specialized detector designed to resolve these domain-specific conflicts. Based on a statistical analysis of ship scales, we introduce a Pyramid Level Shift Strategy that reconfigures the detection head to P2-P4. This shift ensures compliance with Nyquist sampling criteria for small objects while eliminating the computational redundancy of deep layers. To further enhance training stability on high-resolution inputs, we incorporate a Group Normalized Convolutional Block for Linear Projection (GN-CBLinear), which mitigates gradient volatility in micro-batch settings. Validated on SODA-A, DOTA-v1.5, FAIR1M-v2.0, and ShipRSImageNet-V1, LiM-YOLO demonstrates superior detection accuracy and efficiency compared to state-of-the-art models. The code is available at https://github.com/egshkim/LiM-YOLO.