# A semi-supervised Teacher-Student framework for surgical tool detection and localization

arXiv: https://arxiv.org/abs/2208.09926 · HTML: https://mlsanity.com/paper/2208.09926/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Distillation for medical imaging, one of 12 directions in Knowledge distillation.
- Builds on 12 of its 35 references that are in the map.
- First posted on arXiv 21 Aug 2022.

## Placed in

- Knowledge distillation / [Distillation for medical imaging](https://mlsanity.com/distill/distillation-for-medical-imaging/)

## Builds on (most cited first, 12 of 12)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [Tool Detection and Operative Skill Assessment in Surgical Videos Using Region-Based Convolutional Neural Networks](https://mlsanity.com/paper/1802.08774/) (2018)
- [Detection and Localization of Robotic Tools in Robot-Assisted Surgery Videos Using Deep Neural Networks for Region Proposal and Detection](https://mlsanity.com/paper/2008.00936/) (2020)
- [Weakly-Supervised Learning for Tool Localization in Laparoscopic Videos](https://mlsanity.com/paper/1806.05573/) (2018)
- [Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgery](https://mlsanity.com/paper/1710.06668/) (2017)
- [Tool and Phase recognition using contextual CNN features](https://mlsanity.com/paper/1610.08854/) (2016)
- [Single- and Multi-Task Architectures for Tool Presence Detection Challenge at M2CAI 2016](https://mlsanity.com/paper/1610.08851/) (2016)

## Built on by (most cited first, 6 of 6)

- [Surgical Scene Understanding in the Era of Foundation AI Models: A Comprehensive Review](https://mlsanity.com/paper/2502.14886/) (2025)
- [GynSurg: A Comprehensive Gynecology Laparoscopic Surgery Dataset](https://mlsanity.com/paper/2506.11356/) (2025)
- [EgoSurgery-Tool: A Dataset of Surgical Tool and Hand Detection from Egocentric Open Surgery Videos](https://mlsanity.com/paper/2406.03095/) (2024)
- [A comprehensive survey on recent deep learning-based methods applied to surgical data](https://mlsanity.com/paper/2209.01435/) (2022)
- [Weakly Semi-supervised Tool Detection in Minimally Invasive Surgery Videos](https://mlsanity.com/paper/2401.02791/) (2024)
- [Robust Surgical Tools Detection in Endoscopic Videos with Noisy Data](https://mlsanity.com/paper/2307.01232/) (2023)

## Abstract (arXiv)

Surgical tool detection in minimally invasive surgery is an essential part of computer-assisted interventions. Current approaches are mostly based on supervised methods which require large fully labeled data to train supervised models and suffer from pseudo label bias because of class imbalance issues. However large image datasets with bounding box annotations are often scarcely available. Semi-supervised learning (SSL) has recently emerged as a means for training large models using only a modest amount of annotated data; apart from reducing the annotation cost. SSL has also shown promise to produce models that are more robust and generalizable. Therefore, in this paper we introduce a semi-supervised learning (SSL) framework in surgical tool detection paradigm which aims to mitigate the scarcity of training data and the data imbalance through a knowledge distillation approach. In the proposed work, we train a model with labeled data which initialises the Teacher-Student joint learning, where the Student is trained on Teacher-generated pseudo labels from unlabeled data. We propose a multi-class distance with a margin based classification loss function in the region-of-interest head of the detector to effectively segregate foreground classes from background region. Our results on m2cai16-tool-locations dataset indicate the superiority of our approach on different supervised data settings (1%, 2%, 5%, 10% of annotated data) where our model achieves overall improvements of 8%, 12% and 27% in mAP (on 1% labeled data) over the state-of-the-art SSL methods and a fully supervised baseline, respectively. The code is available at https://github.com/Mansoor-at/Semi-supervised-surgical-tool-det