paper-with-me

Papers

DeepATLAS: One-Shot Localization for Biomedical Data

2024-02-14 · Peter D. Chang

This paper introduces the DeepATLAS foundational model for localization tasks in the domain of high-dimensional biomedical data. Upon convergence of the proposed self-supervised objective, a pretrained model maps an input to an anatomically-consistent embedding from which any point or set of points (e.g., boxes or segmentations) may be identified in a one-shot or few-shot approach. As a representative benchmark, a DeepATLAS model pretrained on a comprehensive cohort of 51,000+ unlabeled 3D computed tomography exams yields high one-shot segmentation performance on over 50 anatomic structures across four different external test sets, either matching or exceeding the performance of a standard supervised learning model. Further improvements in accuracy can be achieved by adding a small amount of labeled data using either a semisupervised or more conventional fine-tuning strategy.

📄 PDF Abstract BibTeX arXiv:2402.09587

Code (0)

등록된 구현이 없습니다.

Tasks

One-Shot Segmentation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

DeepAtlas: a tool for effective manifold learning

2025-08-26 · Serena Hughes, Timothy Hamilton, Tom Kolokotrones, Eric J. Deeds arxiv

Manifold learning builds on the "manifold hypothesis," which posits that data in high-dimensional datasets are drawn from lower-dimensional manifolds. Current tools generate global embeddings of data, rather than the loc…

In-Context Adaptation of VLMs for Few-Shot Cell Detection in Optical Microscopy

2025-11-04 · Shreyan Ganguly, Angona Biswas, Jaydeep Rade, Md Hasibul Hasan Hasib 외 arxiv

Foundation vision-language models (VLMs) excel on natural images, but their utility for biomedical microscopy remains underexplored. In this paper, we investigate how in-context learning enables state-of-the-art VLMs to …

Few-Shot Object DetectionCell Detection

From Zero to Hero: Harnessing Transformers for Biomedical Named Entity Recognition in Zero- and Few-shot Contexts

2023-05-05 · Miloš Košprdić, Nikola Prodanović, Adela Ljajić, Bojana Bašaragin 외

Supervised named entity recognition (NER) in the biomedical domain depends on large sets of annotated texts with the given named entities. The creation of such datasets can be time-consuming and expensive, while extracti…

few-shot-nerFew-shot NERnamed-entity-recognitionNamed Entity Recognition+4

GPT-3 Models are Poor Few-Shot Learners in the Biomedical Domain

2021-09-06 · Milad Moradi, Kathrin Blagec, Florian Haberl, Matthias Samwald

Deep neural language models have set new breakthroughs in many tasks of Natural Language Processing (NLP). Recent work has shown that deep transformer language models (pretrained on large amounts of texts) can achieve hi…

Few-Shot LearningLanguage ModellingTransfer Learning

Prompt Combines Paraphrase: Enhancing Biomedical “Pre-training, Prompt and Predicting” Models by Explaining Rare Biomedical Concepts

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Prompt-based fine-tuning for pre-trained models has been proven resultful in general domain for few-shot learning in downstream tasks. As to the biomedical domain, rare biomedical entities, which are quite ubiquitous in …

Few-Shot Learning