Scalpel-SAM: A Semi-Supervised Paradigm for Adapting SAM to Infrared Small Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Zihan, Ren, Xiangning, Kong, Dezhang, Zhang, Yipeng, Han, Meng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912791120576512
author Liu, Zihan
Ren, Xiangning
Kong, Dezhang
Zhang, Yipeng
Han, Meng
author_facet Liu, Zihan
Ren, Xiangning
Kong, Dezhang
Zhang, Yipeng
Han, Meng
contents Infrared small object detection urgently requires semi-supervised paradigms due to the high cost of annotation. However, existing methods like SAM face significant challenges of domain gaps, inability of encoding physical priors, and inherent architectural complexity. To address this, we designed a Hierarchical MoE Adapter consisting of four white-box neural operators. Building upon this core component, we propose a two-stage paradigm for knowledge distillation and transfer: (1) Prior-Guided Knowledge Distillation, where we use our MoE adapter and 10% of available fully supervised data to distill SAM into an expert teacher (Scalpel-SAM); and (2) Deployment-Oriented Knowledge Transfer, where we use Scalpel-SAM to generate pseudo labels for training lightweight and efficient downstream models. Experiments demonstrate that with minimal annotations, our paradigm enables downstream models to achieve performance comparable to, or even surpassing, their fully supervised counterparts. To our knowledge, this is the first semi-supervised paradigm that systematically addresses the data scarcity issue in IR-SOT using SAM as the teacher model.
format Preprint
id arxiv_https___arxiv_org_abs_2512_22483
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scalpel-SAM: A Semi-Supervised Paradigm for Adapting SAM to Infrared Small Object Detection
Liu, Zihan
Ren, Xiangning
Kong, Dezhang
Zhang, Yipeng
Han, Meng
Computer Vision and Pattern Recognition
68T45, 68T07
I.4.6; I.2.6
Infrared small object detection urgently requires semi-supervised paradigms due to the high cost of annotation. However, existing methods like SAM face significant challenges of domain gaps, inability of encoding physical priors, and inherent architectural complexity. To address this, we designed a Hierarchical MoE Adapter consisting of four white-box neural operators. Building upon this core component, we propose a two-stage paradigm for knowledge distillation and transfer: (1) Prior-Guided Knowledge Distillation, where we use our MoE adapter and 10% of available fully supervised data to distill SAM into an expert teacher (Scalpel-SAM); and (2) Deployment-Oriented Knowledge Transfer, where we use Scalpel-SAM to generate pseudo labels for training lightweight and efficient downstream models. Experiments demonstrate that with minimal annotations, our paradigm enables downstream models to achieve performance comparable to, or even surpassing, their fully supervised counterparts. To our knowledge, this is the first semi-supervised paradigm that systematically addresses the data scarcity issue in IR-SOT using SAM as the teacher model.
title Scalpel-SAM: A Semi-Supervised Paradigm for Adapting SAM to Infrared Small Object Detection
topic Computer Vision and Pattern Recognition
68T45, 68T07
I.4.6; I.2.6
url https://arxiv.org/abs/2512.22483