paper-with-me

Papers

VLSM-Adapter: Finetuning Vision-Language Segmentation Efficiently with Lightweight Blocks

2024-05-10 · Manish Dhakal, Rabin Adhikari, Safal Thapaliya, Bishesh Khanal

Foundation Vision-Language Models (VLMs) trained using large-scale open-domain images and text pairs have recently been adapted to develop Vision-Language Segmentation Models (VLSMs) that allow providing text prompts during inference to guide image segmentation. If robust and powerful VLSMs can be built for medical images, it could aid medical professionals in many clinical tasks where they must spend substantial time delineating the target structure of interest. VLSMs for medical images resort to fine-tuning base VLM or VLSM pretrained on open-domain natural image datasets due to fewer annotated medical image datasets; this fine-tuning is resource-consuming and expensive as it usually requires updating all or a significant fraction of the pretrained parameters. Recently, lightweight blocks called adapters have been proposed in VLMs that keep the pretrained model frozen and only train adapters during fine-tuning, substantially reducing the computing resources required. We introduce a novel adapter, VLSM-Adapter, that can fine-tune pretrained vision-language segmentation models using transformer encoders. Our experiments in widely used CLIP-based segmentation models show that with only 3 million trainable parameters, the VLSM-Adapter outperforms state-of-the-art and is comparable to the upper bound end-to-end fine-tuning. The source code is available at: https://github.com/naamiinepal/vlsm-adapter.

📄 PDF Abstract BibTeX arXiv:2405.06196

Code (2)

naamiinepal/vlsm-adapter 공식 구현 pytorch
anjilab/secure-private-ai pytorch

Tasks

Image SegmentationMedical Image SegmentationSegmentationSemantic SegmentationVision-Language Segmentation

Methods 이 논문이 사용한 방법론

Transformer A Transformer is a model architecture that eschews recurrence and instead relies entirely on an [attention…
Adapter 설명 없음

Similar Papers 제목 키워드 기반

Synthetic Boost: Leveraging Synthetic Data for Enhanced Vision-Language Segmentation in Echocardiography

2023-09-22 · Rabin Adhikari, Manish Dhakal, Safal Thapaliya, Kanchan Poudel 외

Accurate segmentation is essential for echocardiography-based assessment of cardiovascular diseases (CVDs). However, the variability among sonographers and the inherent challenges of ultrasound images hinder precise segm…

SegmentationVision-Language Segmentation

Exploring Transfer Learning in Medical Image Segmentation using Vision-Language Models

2023-08-15 · Kanchan Poudel, Manish Dhakal, Prasiddha Bhandari, Rabin Adhikari 외

Medical image segmentation allows quantifying target structure size and shape, aiding in disease diagnosis, prognosis, surgery planning, and comprehension.Building upon recent advancements in foundation Vision-Language M…

Image SegmentationMedical Image SegmentationPrognosisSegmentation+3

Adversarial Robustness Analysis of Vision-Language Models in Medical Image Segmentation

2025-05-05 · Anjila Budathoki, Manish Dhakal

Adversarial attacks have been fairly explored for computer vision and vision-language models. However, the avenue of adversarial attack for the vision language segmentation models (VLSMs) is still under-explored, especia…

Adversarial AttackAdversarial RobustnessImage SegmentationMedical Image Analysis+3

Improvise, Adapt, Overcome -- Telescopic Adapters for Efficient Fine-tuning of Vision Language Models in Medical Imaging

2025-12-15 · Ujjwal Mishra, Vinita Shukla, Praful Hambarde, Amit Shukla arxiv

Adapting Vision Language Segmentation Models (VLSMs) to medical imaging domains requires significant computational overhead when using conventional fine-tuning approaches. Existing Parameter-Efficient Fine-Tuning (PEFT) …

parameter-efficient fine-tuningPolyp Segmentation

VLSM-Ensemble: Ensembling CLIP-based Vision-Language Models for Enhanced Medical Image Segmentation

2025-09-05 · Julia Dietlmeier, Oluwabukola Grace Adegboro, Vayangi Ganepola, Claudia Mazo 외 arxiv

Vision-language models and their adaptations to image segmentation tasks present enormous potential for producing highly accurate and interpretable results. However, implementations based on CLIP and BiomedCLIP are still…

Medical Image SegmentationPrompt Engineering