paper-with-me

Papers

Interpreting Biomedical VLMs on High-Imbalance Out-of-Distributions: An Insight into BiomedCLIP on Radiology

2025-06-17 · Nafiz Sadman, Farhana Zulkernine, Benjamin Kwan

In this paper, we construct two research objectives: i) explore the learned embedding space of BiomedCLIP, an open-source large vision language model, to analyse meaningful class separations, and ii) quantify the limitations of BiomedCLIP when applied to a highly imbalanced, out-of-distribution multi-label medical dataset. We experiment on IU-xray dataset, which exhibits the aforementioned criteria, and evaluate BiomedCLIP in classifying images (radiographs) in three contexts: zero-shot inference, full finetuning, and linear probing. The results show that the model under zero-shot settings over-predicts all labels, leading to poor precision and inter-class separability. Full fine-tuning improves classification of distinct diseases, while linear probing detects overlapping features. We demonstrate visual understanding of the model using Grad-CAM heatmaps and compare with 15 annotations by a radiologist. We highlight the need for careful adaptations of the models to foster reliability and applicability in a real-world setting. The code for the experiments in this work is available and maintained on GitHub.

📄 PDF Abstract BibTeX arXiv:2506.14136

Code (1)

nafiz95/biovlm_eval_cxr 공식 구현

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

A Study of Data Pre-processing Techniques for Imbalanced Biomedical Data Classification

2019-11-04 · Shigang Liu, Jun Zhang, Yang Xiang, Wanlei Zhou 외

Biomedical data are widely accepted in developing prediction models for identifying a specific tumor, drug discovery and classification of human cancers. However, previous studies usually focused on different classifiers…

Drug Discoveryfeature selectionGeneral Classification

Examining Imbalance Effects on Performance and Demographic Fairness of Clinical Language Models

2024-12-23 · Precious Jones, Weisi Liu, I-Chan Huang, Xiaolei Huang

Data imbalance is a fundamental challenge in applying language models to biomedical applications, particularly in ICD code prediction tasks where label and demographic distributions are uneven. While state-of-the-art lan…

Fairness

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification

2026-03-25 · Han Sun, Qin Li, Peixin Wang, Min Zhang arxiv

Object hallucination in Large Vision-Language Models (LVLMs) severely compromises their reliability in real-world applications, posing a critical barrier to their deployment in high-stakes scenarios such as autonomous dr…

Autonomous Driving

From Uncertainty to Clarity: Uncertainty-Guided Class-Incremental Learning for Limited Biomedical Samples via Semantic Expansion

2024-09-12 · Yifei Yao, Hanrong Zhang

In real-world clinical settings, data distributions evolve over time, with a continuous influx of new, limited disease cases. Therefore, class incremental learning is of great significance, i.e., deep learning models are…

class-incremental learningClass Incremental LearningIncremental Learning

ReProCon: Scalable and Resource-Efficient Few-Shot Biomedical Named Entity Recognition

2025-08-22 · Jeongkyun Yoo, Nela Riddle, Andrew Hoblitzell arxiv

Named Entity Recognition (NER) in biomedical domains faces challenges due to data scarcity and imbalanced label distributions, especially with fine-grained entity types. We propose ReProCon, a novel few-shot NER framewor…

Contrastive LearningFew-shot NER