---
title: "H^2Net: Homo- and Heterogeneous Networks for Unified Segmentation"
authors:
  - "Jinyu Han"
  - "Changguang Wu"
  - "Fuming Sun"
  - "Mengyin Wang"
  - "Jinhui Tang"
doi: "10.24963/ijcai.2026/127"
url: "https://ijcai.org/proceedings/2026/127"
pdf: "https://ijcai.org/proceedings/2026/0127.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "1133-1142"
track: "Main Track"
keywords:
  - "Computer Vision: Biomedical image analysis"
  - "Computer Vision: Segmentation, grouping and shape analysis"
  - "Computer Vision: Multimodal learning"
---

# H^2Net: Homo- and Heterogeneous Networks for Unified Segmentation

Jinyu Han, Changguang Wu, Fuming Sun, Mengyin Wang, Jinhui Tang

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 1133-1142. DOI: [10.24963/ijcai.2026/127](https://doi.org/10.24963/ijcai.2026/127)

## Abstract

Unified segmentation aims to consolidate multiple vision tasks into a single model, yet faces two core challenges: learning robust homogeneous features (e.g., shared low- and mid-level cues) to enable cross-domain knowledge transfer, while disentangling heterogeneous features (e.g., task-specific semantic objectives) to avoid negative transfer and preserve task independence.
To address these challenges, we propose the Homo- and Heterogeneous Network (H2Net), a unified framework that jointly models shared homogeneous representations and task-specific heterogeneous features. Specifically, H2Net incorporates a Cross-Modal Structure Enhancement Module (CSEM), which integrates auxiliary depth priors via joint frequency–spatial cross-modal attention to strengthen task-agnostic structural representations. In addition, a Task Adapter Pool (TAP) is introduced to model task-specific heterogeneous features by assigning dedicated adapters to individual tasks, enabling task-aware feature modulation and semantic disentanglement within a shared backbone. Extensive experiments on benchmarks spanning eight tasks demonstrate the effectiveness of the proposed approach and its superior performance. Code and results will be available at https://h2net-ijcai26.github.io.