paper-with-me

Papers

In-Context Multiple Instance Learning

2026-06-04 · Alexander Möllers, Marvin Sextro, Julius Hense, Gabriel Dernbach, Klaus-Robert Müller arxiv

Multiple Instance Learning (MIL) addresses problems where supervision is available at the level of bags of instances and has been successfully applied in fields ranging from computational pathology to satellite imagery. Nevertheless, existing algorithms struggle in the low-label regime that characterizes many real-world applications. Flexible models overfit and rigid ones fail to adapt to the task at hand. We show that pretraining an in-context learner with a Perceiver-style architecture on synthetic data yields a model that can solve new tasks from a handful of labeled bags. At inference time, classification happens in a single forward pass and requires no gradient updates. We propose and investigate different synthetic data generators for bag-structured data and find that they capture complementary inductive biases. A model pretrained on a mixture of these generators inherits their per-task strengths and achieves the best average performance across twelve MIL benchmarks, outperforming supervised baselines that require task-specific training.

📄 PDF Abstract BibTeX arXiv:2606.06458

Code (0)

등록된 구현이 없습니다.

Tasks

Multiple Instance Learning

Similar Papers 제목 키워드 기반

LadderMIL: Multiple Instance Learning with Coarse-to-Fine Self-Distillation

2025-02-04 · Shuyang Wu, Yifu Qiu, Ines P. Nearchou, Sandrine Prost 외

Multiple Instance Learning (MIL) for whole slide image (WSI) analysis in computational pathology often neglects instance-level learning as supervision is typically provided only at the bag level. In this work, we present…

BenchmarkingClassificationMultiple Instance LearningPrognosis+1

ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation

2025-10-13 · Ruihang Xu, Dewei Zhou, Fan Ma, Yi Yang arxiv

Multi-instance image generation (MIG) remains a significant challenge for modern diffusion models due to key limitations in achieving precise control over object layout and preserving the identity of multiple distinct su…

Image Generation

CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images

2023-05-09 · Olga Fourkioti, Matt De Vries, Chen Jin, Daniel C. Alexander 외

The visual examination of tissue biopsy sections is fundamental for cancer diagnosis, with pathologists analyzing sections at multiple magnifications to discern tumor cells and their subtypes. However, existing attention…

DiagnosticImage ClassificationMultiple Instance LearningMultiple Instance LearningMultiple Instance Learning+2

An analysis of ambiguity in word sense annotations

2014-05-01 · LREC 2014 5 · David Jurgens

Word sense annotation is a challenging task where annotators distinguish which meaning of a word is present in a given context. In some contexts, a word usage may elicit multiple interpretations, resulting either in anno…

Word Sense Disambiguation

Contextualizing Meta-Learning via Learning to Decompose

2021-06-15 · Han-Jia Ye, Da-Wei Zhou, Lanqing Hong, Zhenguo Li 외

Meta-learning has emerged as an efficient approach for constructing target models based on support sets. For example, the meta-learned embeddings enable the construction of target nearest-neighbor classifiers for specifi…

AttributeFew-Shot Image Classificationimage-classificationImage Classification+1