Saved in:
Bibliographic Details
Main Authors: Thai, Le-Van, Nguyen, Tien Dat, Pham, Hoai Nhan, Thi, Lan Anh Dinh, Nguyen, Duy-Dong, Bui, Ngoc Lam Quang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.09169
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908951754309632
author Thai, Le-Van
Nguyen, Tien Dat
Pham, Hoai Nhan
Thi, Lan Anh Dinh
Nguyen, Duy-Dong
Bui, Ngoc Lam Quang
author_facet Thai, Le-Van
Nguyen, Tien Dat
Pham, Hoai Nhan
Thi, Lan Anh Dinh
Nguyen, Duy-Dong
Bui, Ngoc Lam Quang
contents Semi-supervised semantic segmentation in computational pathology remains challenging due to scarce pixel-level annotations and unreliable pseudo-label supervision. We propose UniSemAlign, a dual-modal semantic alignment framework that enhances visual segmentation by injecting explicit class-level structure into pixel-wise learning. Built upon a pathology-pretrained Transformer encoder, UniSemAlign introduces complementary prototype-level and text-level alignment branches in a shared embedding space, providing structured guidance that reduces class ambiguity and stabilizes pseudo-label refinement. The aligned representations are fused with visual predictions to generate more reliable supervision for unlabeled histopathology images. The framework is trained end-to-end with supervised segmentation, cross-view consistency, and cross-modal alignment objectives. Extensive experiments on the GlaS and CRAG datasets demonstrate that UniSemAlign substantially outperforms recent semi-supervised baselines under limited supervision, achieving Dice improvements of up to 2.6% on GlaS and 8.6% on CRAG with only 10% labeled data, and strong improvements at 20% supervision. Code is available at: https://github.com/thailevann/UniSemAlign
format Preprint
id arxiv_https___arxiv_org_abs_2604_09169
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle UniSemAlign: Text-Prototype Alignment with a Foundation Encoder for Semi-Supervised Histopathology Segmentation
Thai, Le-Van
Nguyen, Tien Dat
Pham, Hoai Nhan
Thi, Lan Anh Dinh
Nguyen, Duy-Dong
Bui, Ngoc Lam Quang
Computer Vision and Pattern Recognition
Semi-supervised semantic segmentation in computational pathology remains challenging due to scarce pixel-level annotations and unreliable pseudo-label supervision. We propose UniSemAlign, a dual-modal semantic alignment framework that enhances visual segmentation by injecting explicit class-level structure into pixel-wise learning. Built upon a pathology-pretrained Transformer encoder, UniSemAlign introduces complementary prototype-level and text-level alignment branches in a shared embedding space, providing structured guidance that reduces class ambiguity and stabilizes pseudo-label refinement. The aligned representations are fused with visual predictions to generate more reliable supervision for unlabeled histopathology images. The framework is trained end-to-end with supervised segmentation, cross-view consistency, and cross-modal alignment objectives. Extensive experiments on the GlaS and CRAG datasets demonstrate that UniSemAlign substantially outperforms recent semi-supervised baselines under limited supervision, achieving Dice improvements of up to 2.6% on GlaS and 8.6% on CRAG with only 10% labeled data, and strong improvements at 20% supervision. Code is available at: https://github.com/thailevann/UniSemAlign
title UniSemAlign: Text-Prototype Alignment with a Foundation Encoder for Semi-Supervised Histopathology Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.09169