Saved in:
Bibliographic Details
Main Authors: Yang, Chunze, Zhao, Wenjie, Tang, Yue, Lu, Junbo, Ge, Jiusong, Liu, Qidong, Gao, Zeyu, Li, Chen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.17405
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915752928346112
author Yang, Chunze
Zhao, Wenjie
Tang, Yue
Lu, Junbo
Ge, Jiusong
Liu, Qidong
Gao, Zeyu
Li, Chen
author_facet Yang, Chunze
Zhao, Wenjie
Tang, Yue
Lu, Junbo
Ge, Jiusong
Liu, Qidong
Gao, Zeyu
Li, Chen
contents Precision pathology relies on detecting fine-grained morphological abnormalities within specific Regions of Interest (ROIs), as these local, texture-rich cues - rather than global slide contexts - drive expert diagnostic reasoning. While Vision-Language (V-L) models promise data efficiency by leveraging semantic priors, adapting them faces a critical Granularity Mismatch, where generic representations fail to resolve such subtle defects. Current adaptation methods often treat modalities as independent streams, failing to ground semantic prompts in ROI-specific visual contexts. To bridge this gap, we propose the Hierarchical Adaptation and Alignment Framework (HAAF). At its core is a novel Cross-Level Scaled Alignment (CLSA) mechanism that enforces a sequential calibration order: visual features first inject context into text prompts to generate content-adaptive descriptors, which then spatially guide the visual encoder to spotlight anomalies. Additionally, a dual-branch inference strategy integrates semantic scores with geometric prototypes to ensure stability in few-shot settings. Experiments on four benchmarks show HAAF significantly outperforms state-of-the-art methods and effectively scales with domain-specific backbones (e.g., CONCH) in low-resource scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17405
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HAAF: Hierarchical Adaptation and Alignment of Foundation Models for Few-Shot Pathology Anomaly Detection
Yang, Chunze
Zhao, Wenjie
Tang, Yue
Lu, Junbo
Ge, Jiusong
Liu, Qidong
Gao, Zeyu
Li, Chen
Computer Vision and Pattern Recognition
Precision pathology relies on detecting fine-grained morphological abnormalities within specific Regions of Interest (ROIs), as these local, texture-rich cues - rather than global slide contexts - drive expert diagnostic reasoning. While Vision-Language (V-L) models promise data efficiency by leveraging semantic priors, adapting them faces a critical Granularity Mismatch, where generic representations fail to resolve such subtle defects. Current adaptation methods often treat modalities as independent streams, failing to ground semantic prompts in ROI-specific visual contexts. To bridge this gap, we propose the Hierarchical Adaptation and Alignment Framework (HAAF). At its core is a novel Cross-Level Scaled Alignment (CLSA) mechanism that enforces a sequential calibration order: visual features first inject context into text prompts to generate content-adaptive descriptors, which then spatially guide the visual encoder to spotlight anomalies. Additionally, a dual-branch inference strategy integrates semantic scores with geometric prototypes to ensure stability in few-shot settings. Experiments on four benchmarks show HAAF significantly outperforms state-of-the-art methods and effectively scales with domain-specific backbones (e.g., CONCH) in low-resource scenarios.
title HAAF: Hierarchical Adaptation and Alignment of Foundation Models for Few-Shot Pathology Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.17405