Unleashing the Power of Generic Segmentation Models: A Simple Baseline for Infrared Small Target Detection

TL;DR

This paper explores adapting generic segmentation models like SAM for infrared small target detection, proposing a lightweight baseline that, with distillation and novel query design, surpasses state-of-the-art methods in accuracy and efficiency.

Contribution

It introduces a simple, effective baseline model for IRSTD that leverages distillation and multi-scale query design to outperform existing specialized methods.

Findings

Our model surpasses SAM and Semantic-SAM by over 14 IoU on NUDT.

It outperforms state-of-the-art IRSTD methods in accuracy.

The approach improves both accuracy and throughput across datasets.

Abstract

Recent advancements in deep learning have greatly advanced the field of infrared small object detection (IRSTD). Despite their remarkable success, a notable gap persists between these IRSTD methods and generic segmentation approaches in natural image domains. This gap primarily arises from the significant modality differences and the limited availability of infrared data. In this study, we aim to bridge this divergence by investigating the adaptation of generic segmentation models, such as the Segment Anything Model (SAM), to IRSTD tasks. Our investigation reveals that many generic segmentation models can achieve comparable performance to state-of-the-art IRSTD methods. However, their full potential in IRSTD remains untapped. To address this, we propose a simple, lightweight, yet effective baseline model for segmenting small infrared objects. Through appropriate distillation strategies, we empower smaller student models to outperform state-of-the-art methods, even surpassing fine-tuned teacher results. Furthermore, we enhance the model's performance by introducing a novel query design comprising dense and sparse queries to effectively encode multi-scale features. Through extensive experimentation across four popular IRSTD datasets, our model demonstrates significantly improved performance in both accuracy and throughput compared to existing approaches, surpassing SAM and Semantic-SAM by over 14 IoU on NUDT and 4 IoU on IRSTD1k. The source code and models will be released at https://github.com/O937-blip/SimIR.