paper-with-me

홈 › Papers

Synthetic Data Reveals Generalization Gaps in Correlated Multiple Instance Learning

2025-10-29 · Ethan Harvey, Dennis Johan Loevlie, Michael C. Hughes arxiv

Multiple instance learning (MIL) is often used in medical imaging to classify high-resolution 2D images by processing patches or classify 3D volumes by processing slices. However, conventional MIL approaches treat instances separately, ignoring contextual relationships such as the appearance of nearby patches or slices that can be essential in real applications. We design a synthetic classification task where accounting for adjacent instance features is crucial for accurate prediction. We demonstrate the limitations of off-the-shelf MIL approaches by quantifying their performance compared to the optimal Bayes estimator for this task, which is available in closed-form. We empirically show that newer correlated MIL methods still do not achieve the best possible performance when trained with ten thousand training samples, each containing many instances.

📄 PDF Abstract BibTeX arXiv:2510.25759

Code (0)

등록된 구현이 없습니다.

Tasks

Multiple Instance Learning

Similar Papers 제목 키워드 기반

Domain Generalization with Correlated Style Uncertainty

2022-12-20 · Zheyuan Zhang, Bin Wang, Debesh Jha, Ugur Demir 외

Domain generalization (DG) approaches intend to extract domain invariant features that can lead to a more robust deep learning model. In this regard, style augmentation is a strong DG method taking advantage of instance-…

Domain GeneralizationRetrieval

Sequential training of GANs against GAN-classifiers reveals correlated "knowledge gaps" present among independently trained GAN instances

2023-03-27 · CVPR 2023 1 · Arkanath Pathak, Nicholas Dufour

Modern Generative Adversarial Networks (GANs) generate realistic images remarkably well. Previous work has demonstrated the feasibility of "GAN-classifiers" that are distinct from the co-trained discriminator, and operat…

Multi-Armed Bandits with Correlated Arms

2019-11-06 · Samarth Gupta, Shreyas Chaudhari, Gauri Joshi, Osman Yağan

We consider a multi-armed bandit framework where the rewards obtained by pulling different arms are correlated. We develop a unified approach to leverage these reward correlations and present fundamental generalizations …

Multi-Armed Bandits

Value-order Decomposition for Generalist Anomaly Detection

2026-06-12 · Miaoyun Zhao, Jing Chen, Miaoni Zhao, Qiang Zhang arxiv

Industrial anomaly detection suffers from limited data, making cross-domain generalization particularly challenging. Generalist Anomaly Detection (GAD) aims to train a unified model on a source domain that can effectivel…

Domain GeneralizationAnomaly Detection

On the Equivalency, Substitutability, and Flexibility of Synthetic Data

2024-03-24 · Che-Jui Chang, Danrui Li, Seonghyeon Moon, Mubbasir Kapadia

We study, from an empirical standpoint, the efficacy of synthetic data in real-world scenarios. Leveraging synthetic data for training perception models has become a key strategy embraced by the community due to its effi…