TY - GEN
T1 - Neighbor Does Matter
T2 - 39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025
AU - Tang, Feilong
AU - Xu, Zhongxing
AU - Hu, Ming
AU - Li, Wenxue
AU - Xia, Peng
AU - Zhong, Yiheng
AU - Wu, Hanjun
AU - Su, Jionglong
AU - Ge, Zongyuan
N1 - Publisher Copyright:
Copyright © 2025, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2025/4/11
Y1 - 2025/4/11
N2 - In medical image analysis, multi-organ semi-supervised segmentation faces challenges such as insufficient labels and low contrast in soft tissues. To address these issues, existing studies typically employ semi-supervised segmentation techniques using pseudo-labeling and consistency regularization. However, these methods mainly rely on individual data samples for training, ignoring the rich neighborhood information present in the feature space. In this work, we argue that supervisory information can be directly extracted from the geometry of the feature space. Inspired by the density-based clustering hypothesis, we propose using feature density to locate sparse regions within feature clusters. Our goal is to increase intra-class compactness by addressing sparsity issues. To achieve this, we propose a Density-Aware Contrastive Learning (DACL) strategy, pushing anchored features in sparse regions towards cluster centers approximated by high-density positive samples, resulting in more compact clusters. Specifically, our method constructs density-aware neighbor graphs using labeled and unlabeled data samples to estimate feature density and locate sparse regions. We also combine label-guided co-training with density-guided geometric regularization to form complementary supervision for unlabeled data. Experiments on the Multi-Organ Segmentation Challenge dataset demonstrate that our proposed method outperforms state-of-the-art methods, highlighting its efficacy in medical image segmentation tasks.
AB - In medical image analysis, multi-organ semi-supervised segmentation faces challenges such as insufficient labels and low contrast in soft tissues. To address these issues, existing studies typically employ semi-supervised segmentation techniques using pseudo-labeling and consistency regularization. However, these methods mainly rely on individual data samples for training, ignoring the rich neighborhood information present in the feature space. In this work, we argue that supervisory information can be directly extracted from the geometry of the feature space. Inspired by the density-based clustering hypothesis, we propose using feature density to locate sparse regions within feature clusters. Our goal is to increase intra-class compactness by addressing sparsity issues. To achieve this, we propose a Density-Aware Contrastive Learning (DACL) strategy, pushing anchored features in sparse regions towards cluster centers approximated by high-density positive samples, resulting in more compact clusters. Specifically, our method constructs density-aware neighbor graphs using labeled and unlabeled data samples to estimate feature density and locate sparse regions. We also combine label-guided co-training with density-guided geometric regularization to form complementary supervision for unlabeled data. Experiments on the Multi-Organ Segmentation Challenge dataset demonstrate that our proposed method outperforms state-of-the-art methods, highlighting its efficacy in medical image segmentation tasks.
UR - http://www.scopus.com/inward/record.url?scp=105003998897&partnerID=8YFLogxK
U2 - 10.1609/aaai.v39i7.32776
DO - 10.1609/aaai.v39i7.32776
M3 - Conference Proceeding
AN - SCOPUS:105003998897
T3 - Proceedings of the AAAI Conference on Artificial Intelligence
SP - 7220
EP - 7228
BT - Special Track on AI Alignment
A2 - Walsh, Toby
A2 - Shah, Julie
A2 - Kolter, Zico
PB - Association for the Advancement of Artificial Intelligence
Y2 - 25 February 2025 through 4 March 2025
ER -