Is Bigger Always Better? Efficiency Analysis in Resource-Constrained Small Object Detection

TL;DR

This study systematically analyzes the efficiency of small object detection models in resource-constrained Earth observation, revealing that smaller, high-resolution models can outperform larger ones in both efficiency and accuracy.

Contribution

It provides the first comprehensive efficiency analysis across model size, dataset size, and resolution in resource-limited EO, challenging the assumption that bigger models are always better.

Findings

Resolution significantly boosts efficiency (+120%)

Small high-resolution models outperform larger ones in efficiency and accuracy

Additional data yields minimal gains at low resolution

Abstract

Scaling laws assume larger models trained on more data consistently outperform smaller ones -- an assumption that drives model selection in computer vision but remains untested in resource-constrained Earth observation (EO). We conduct a systematic efficiency analysis across three scaling dimensions: model size, dataset size, and input resolution, on rooftop PV detection in Madagascar. Optimizing for model efficiency (mAP$_{50}$ per unit of model size), we find a consistent efficiency inversion: YOLO11N achieves both the highest efficiency ($24\times$ higher than YOLO11X) and the highest absolute mAP$_{50}$ (0.617). Resolution is the dominant resource allocation lever ($+$120% efficiency gain), while additional data yields negligible returns at low resolution. These findings are robust to the deployment objective: small high-resolution configurations are Pareto-dominant across all 44 setups in the joint accuracy-throughput space, leaving no tradeoff to resolve. In data-scarce EO, bigger is not just unnecessary: it can be worse.