In-Context Multiple Instance Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Multiple Instance LearningSimilar Papers 제목 키워드 기반
LadderMIL: Multiple Instance Learning with Coarse-to-Fine Self-Distillation
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+1ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation
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 GenerationCAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images
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+2An analysis of ambiguity in word sense annotations
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 DisambiguationContextualizing Meta-Learning via Learning to Decompose
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