ACE-LoRA: Graph-Attentive Context Enhancement for Parameter-Efficient Adaptation of Medical Vision-Language Models

TL;DR

ACE-LoRA introduces a parameter-efficient framework that enhances medical vision-language models with higher-order contextual understanding and label-guided training, significantly improving zero-shot performance across various medical imaging tasks.

Contribution

It proposes ACE-LoRA, a novel adaptation method combining LoRA modules and ACE-HGNN to improve fine-grained diagnostic understanding in generalist medical VLMs.

Findings

Outperforms state-of-the-art medical VLMs and PEFT baselines.

Achieves superior zero-shot classification, segmentation, and detection results.

Adds only 0.95M trainable parameters.

Abstract

The success of CLIP-like vision-language models (VLMs) on natural images has inspired medical counterparts, yet existing approaches largely fall into two extremes: specialist models trained on single-domain data, which capture domain-specific details but generalize poorly, and generalist medical VLMs trained on multi-domain data, which retain broad semantics but dilute fine-grained diagnostic cues. Bridging this specialization-generalization trade-off remains challenging. To address this problem, we propose ACE-LoRA, a parameter-efficient adaptation framework for generalist medical VLMs that maintains robust zero-shot generalization. ACE-LoRA integrates Low-Rank Adaptation (LoRA) modules into frozen image-text encoders and introduces an Attention-based Context Enhancement Hypergraph Neural Network (ACE-HGNN) module that captures higher-order contextual interactions beyond pairwise similarity to enrich global representations with localized diagnostic cues, addressing a key limitation of prior Parameter-Efficient Fine-Tuning (PEFT) methods that overlook fine-grained details. To further enhance cross-modal alignment, we formulate a label-guided InfoNCE loss to effectively suppress false negatives between semantically related image-text pairs. Despite adding only 0.95M trainable parameters, ACE-LoRA consistently outperforms state-of-the-art medical VLMs and PEFT baselines across zero-shot classification, segmentation, and detection benchmarks spanning multiple domains. Our code is available at https://github.com/icon-lab/ACE-LoRA.