LiM-YOLO: Less is More with Pyramid Level Shift and Normalized Auxiliary Branch for Ship Detection in Optical Remote Sensing Imagery

TL;DR

LiM-YOLO introduces a streamlined ship detection model that reconfigures feature pyramid levels and employs group normalization, achieving high accuracy with fewer parameters on multiple satellite imagery benchmarks.

Contribution

The paper proposes a Pyramid Level Shift Strategy and a Group Normalized Convolutional Block to improve ship detection efficiency and accuracy in satellite imagery.

Findings

Achieves state-of-the-art accuracy on multiple benchmarks.

Uses fewer parameters than existing methods.

Effectively stabilizes training with high-resolution inputs.

Abstract

Applying general-purpose object detectors to ship detection in satellite imagery presents significant challenges due to the extreme scale disparity and high aspect ratios of maritime targets. In conventional YOLO architectures, the deepest feature pyramid level (P5, stride of 32) compresses narrow vessels into sub-pixel representations, causing severe spatial feature dilution that prevents the network from resolving fine-grained ship boundaries. In this work, we propose LiM-YOLO (Less is More YOLO), a streamlined detector designed to address these domain-specific structural conflicts. Through a statistical analysis of ship scale distributions across four major benchmarks, we introduce a Pyramid Level Shift Strategy that reconfigures the detection head from the conventional P3-P5 to P2-P4. This shift ensures compliance with the Nyquist sampling condition for small targets while eliminating the computational redundancy inherent in the deep P5 layers. To further stabilize training on high-resolution satellite inputs, we incorporate a Group Normalized Convolutional Block for Linear Projection (GN-CBLinear), which replaces batch-dependent normalization with Group Normalization to overcome gradient instability in memory-constrained micro-batch regimes. Validated on SODA-A, DOTA-v1.5, FAIR1M-v2.0, and ShipRSImageNet-V1, LiM-YOLO achieves state-of-the-art detection accuracy with significantly fewer parameters than existing methods, validating that a well-targeted pyramid level shift can achieve a "Less is More" balance between accuracy and efficiency. The code is available at https://github.com/egshkim/LiM-YOLO.