Saved in:
Bibliographic Details
Main Authors: Duangprom, Krit, Lambrou, Tryphon, Bhattarai, Binod
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.20830
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916923656110080
author Duangprom, Krit
Lambrou, Tryphon
Bhattarai, Binod
author_facet Duangprom, Krit
Lambrou, Tryphon
Bhattarai, Binod
contents This paper presents a novel pipeline for 2D keypoint estima- tion of surgical tools by leveraging Vision Language Models (VLMs) fine- tuned using a low rank adjusting (LoRA) technique. Unlike traditional Convolutional Neural Network (CNN) or Transformer-based approaches, which often suffer from overfitting in small-scale medical datasets, our method harnesses the generalization capabilities of pre-trained VLMs. We carefully design prompts to create an instruction-tuning dataset and use them to align visual features with semantic keypoint descriptions. Experimental results show that with only two epochs of fine tuning, the adapted VLM outperforms the baseline models, demonstrating the ef- fectiveness of LoRA in low-resource scenarios. This approach not only improves keypoint detection performance, but also paves the way for future work in 3D surgical hands and tools pose estimation.
format Preprint
id arxiv_https___arxiv_org_abs_2508_20830
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Estimating 2D Keypoints of Surgical Tools Using Vision-Language Models with Low-Rank Adaptation
Duangprom, Krit
Lambrou, Tryphon
Bhattarai, Binod
Computer Vision and Pattern Recognition
This paper presents a novel pipeline for 2D keypoint estima- tion of surgical tools by leveraging Vision Language Models (VLMs) fine- tuned using a low rank adjusting (LoRA) technique. Unlike traditional Convolutional Neural Network (CNN) or Transformer-based approaches, which often suffer from overfitting in small-scale medical datasets, our method harnesses the generalization capabilities of pre-trained VLMs. We carefully design prompts to create an instruction-tuning dataset and use them to align visual features with semantic keypoint descriptions. Experimental results show that with only two epochs of fine tuning, the adapted VLM outperforms the baseline models, demonstrating the ef- fectiveness of LoRA in low-resource scenarios. This approach not only improves keypoint detection performance, but also paves the way for future work in 3D surgical hands and tools pose estimation.
title Estimating 2D Keypoints of Surgical Tools Using Vision-Language Models with Low-Rank Adaptation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.20830