arXiv：cs.LG（机器学习，全量分类）· Duong M. Nguyen, Trong Nghia Hoang, Hang Thi Nguyen, Thanh Trung Huynh, Phi Le Nguyen, Minh N. Do·· 13 小时前AI 评分39
NICER：面向自监督全切片图像压缩的非参数分布匹配框架
Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation
AI 导读
研究提出 NICER，将全切片图像（WSI）的自监督数据压缩重新表述为固定表征视角下的分布匹配问题，用带切片自适应能力的非参数先验实现可计算近似。在五个组织病理学数据集上，NICER 平均准确率较此前方法提升 7.44%，并改善了效率与精度的权衡，同时通过了认证病理学家的临床评估。代码已开源，论文被 NeurIPS 2026 与 SPIGM@ICML 2026 接收。
正文
Abstract:Histological whole-slide images (WSIs) are central to computational pathology but pose severe computational challenges due to their extremely high resolution, often spanning several gigabytes per slide. To enable scalable learning, existing methods apply self-supervised data condensation to reduce computational cost, but typically rely on heuristic prototype learning and do not explicitly preserve learning-relevant feature distributions for downstream tasks. In response, we introduce a principled reformulation of WSI condensation as a distribution-matching problem under a fixed representational lens, and develop NICER, a tractable approximation framework based on a nonparametric prior with slide-adaptive capacity. Experiments on five histopathology datasets, together with clinical evaluation from a board-certified pathologist, show that NICER consistently outperforms prior methods, achieving an average accuracy improvement of 7.44% while offering improved efficiency-accuracy trade-offs, highlighting the benefits of principled, distribution-aware condensation for scalable histological representation learning. Source codes are available in this https URL.
| Comments: | Accepted at NeurIPS 2026, SPIGM@ICML 2026 |
| Subjects: | Image and Video Processing (eess.IV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.00678 [eess.IV] |
| (or arXiv:2610.00678v1 [eess.IV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00678 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Duong M. Nguyen [view email]
[v1]
Wed, 30 Sep 2026 20:15:54 UTC (22,906 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org