# Learning to "Segment Anything" in Thermal Infrared Images through Knowledge Distillation with a Large Scale Dataset SATIR

arXiv: https://arxiv.org/abs/2304.07969 · HTML: https://mlsanity.com/paper/2304.07969/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 6 of its 11 references that are in the map.
- First posted on arXiv 17 Apr 2023.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 6 of 6)

- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Fast Human Pose Estimation](https://mlsanity.com/paper/1811.05419/) (2018)
- [Self-supervised Knowledge Distillation Using Singular Value Decomposition](https://mlsanity.com/paper/1807.06819/) (2018)
- [Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation](https://mlsanity.com/paper/1907.10303/) (2019)
- [Conditional Teacher-Student Learning](https://mlsanity.com/paper/1904.12399/) (2019)

## Built on by (most cited first, 11 of 11)

- [Segment Anything in Medical Images](https://mlsanity.com/paper/2304.12306/) (2023)
- [A Comprehensive Survey on Segment Anything Model for Vision and Beyond](https://mlsanity.com/paper/2305.08196/) (2023)
- [A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering](https://mlsanity.com/paper/2306.06211/) (2023)
- [Knowledge distillation with Segment Anything (SAM) model for Planetary Geological Mapping](https://mlsanity.com/paper/2305.07586/) (2023)
- [SAM-based instance segmentation models for the automation of structural damage detection](https://mlsanity.com/paper/2401.15266/) (2024)
- [SAM for Poultry Science](https://mlsanity.com/paper/2305.10254/) (2023)
- [SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation](https://mlsanity.com/paper/2407.16682/) (2024)
- [RASMD: RGB And SWIR Multispectral Driving Dataset for Robust Perception in Adverse Conditions](https://mlsanity.com/paper/2504.07603/) (2025)
- [An unsupervised approach towards promptable defect segmentation in laser-based additive manufacturing by Segment Anything](https://mlsanity.com/paper/2312.04063/) (2023)
- [Walk the Lines 2: Contour Tracking for Detailed Segmentation](https://mlsanity.com/paper/2511.05210/) (2025)
- [Don't waste SAM](https://mlsanity.com/paper/2606.10696/) (2026)

## Abstract (arXiv)

The Segment Anything Model (SAM) is a promptable segmentation model recently introduced by Meta AI that has demonstrated its prowess across various fields beyond just image segmentation. SAM can accurately segment images across diverse fields, and generating various masks. We discovered that this ability of SAM can be leveraged to pretrain models for specific fields. Accordingly, we have proposed a framework that utilizes SAM to generate pseudo labels for pretraining thermal infrared image segmentation tasks. Our proposed framework can effectively improve the accuracy of segmentation results of specific categories beyond the SOTA ImageNet pretrained model. Our framework presents a novel approach to collaborate with models trained with large data like SAM to address problems in special fields. Also, we generated a large scale thermal infrared segmentation dataset used for pretaining, which contains over 100,000 images with pixel-annotation labels. This approach offers an effective solution for working with large models in special fields where label annotation is challenging. Our code is available at https://github.com/chenjzBUAA/SATIR