Infrared Object Detection with Ultra Small ConvNets: Is ImageNet Pretraining Still Useful?

TL;DR

This paper investigates the impact of ImageNet pretraining on ultra-small infrared object detection models, revealing that pretraining remains beneficial but offers diminishing returns as model size decreases, affecting robustness in varied conditions.

Contribution

The study systematically evaluates the effect of ImageNet pretraining on ultra-small models for infrared detection, providing insights into their robustness and practical recommendations.

Findings

Pretraining improves ultra-small model performance.

Diminishing returns of pretraining beyond a size threshold.

Smaller models are less robust to out-of-distribution data.

Abstract

Many real-world applications require recognition models that are robust to different operational conditions and modalities, but at the same time run on small embedded devices, with limited hardware. While for normal size models, pre-training is known to be very beneficial in accuracy and robustness, for small models, that can be employed for embedded and edge devices, its effect is not clear. In this work, we investigate the effect of ImageNet pretraining on increasingly small backbone architectures (ultra-small models, with less than 1M parameters) with respect to robustness in downstream object detection tasks in the infrared visual modality. Using scaling laws derived from standard object recognition architectures, we construct two ultra-small backbone families and systematically study their performance. Our experiments on three different datasets reveal that while ImageNet pre-training is still useful, beyond a certain capacity threshold, it offers diminishing returns in terms of out-of-distribution detection robustness. Therefore, we advise practitioners to still use pre-training and, when possible avoid too small models as while they might work well for in-domain problems, they are brittle when working conditions are different.