paper-with-me

Papers

Bag-Level Aggregation for Multiple Instance Active Learning in Instance Classification Problems

2017-10-06 · Marc-André Carbonneau, Eric Granger, Ghyslain Gagnon

A growing number of applications, e.g. video surveillance and medical image analysis, require training recognition systems from large amounts of weakly annotated data while some targeted interactions with a domain expert are allowed to improve the training process. In such cases, active learning (AL) can reduce labeling costs for training a classifier by querying the expert to provide the labels of most informative instances. This paper focuses on AL methods for instance classification problems in multiple instance learning (MIL), where data is arranged into sets, called bags, that are weakly labeled. Most AL methods focus on single instance learning problems. These methods are not suitable for MIL problems because they cannot account for the bag structure of data. In this paper, new methods for bag-level aggregation of instance informativeness are proposed for multiple instance active learning (MIAL). The \textit{aggregated informativeness} method identifies the most informative instances based on classifier uncertainty, and queries bags incorporating the most information. The other proposed method, called \textit{cluster-based aggregative sampling}, clusters data hierarchically in the instance space. The informativeness of instances is assessed by considering bag labels, inferred instance labels, and the proportion of labels that remain to be discovered in clusters. Both proposed methods significantly outperform reference methods in extensive experiments using benchmark data from several application domains. Results indicate that using an appropriate strategy to address MIAL problems yields a significant reduction in the number of queries needed to achieve the same level of performance as single instance AL methods.

📄 PDF Abstract BibTeX arXiv:1710.02584

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningGeneral ClassificationInformativenessMedical Image AnalysisMultiple Instance Learning

Similar Papers 제목 키워드 기반

Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification

2019-06-16 · ACL 2019 7 · Zhi-Xiu Ye, Zhen-Hua Ling

This paper presents a multi-level matching and aggregation network (MLMAN) for few-shot relation classification. Previous studies on this topic adopt prototypical networks, which calculate the embedding vector of a query…

Few-Shot Relation ClassificationGeneral ClassificationRelationRelation Classification

Multiple instance active learning for object detection

2021-04-06 · CVPR 2021 1 · Tianning Yuan, Fang Wan, Mengying Fu, Jianzhuang Liu 외

Despite the substantial progress of active learning for image recognition, there still lacks an instance-level active learning method specified for object detection. In this paper, we propose Multiple Instance Active Obj…

Active LearningActive Object DetectionMultiple Instance LearningObject+2

Active Deep Multiple Instance Learning

2021-09-29 · Hitesh Sapkota, Qi Yu

State-of-the-art multiple instance learning (MIL) models achieve competitive performance at the bag level. However, instance-level prediction, which is essential for many important applications, remains largely unsatisfa…

Multiple Instance LearningPrediction

Multiple-Instance Active Learning

2007-12-01 · NeurIPS 2007 12 · Burr Settles, Mark Craven, Soumya Ray

In a multiple instance (MI) learning problem, instances are naturally organized into bags and it is the bags, instead of individual instances, that are labeled for training. MI learners assume that every instance in a ba…

Active Learningtext-classificationText Classification

Balancing Bias and Variance for Active Weakly Supervised Learning

2022-06-12 · Hitesh Sapkota, Qi Yu

As a widely used weakly supervised learning scheme, modern multiple instance learning (MIL) models achieve competitive performance at the bag level. However, instance-level prediction, which is essential for many importa…

Multiple Instance LearningPredictionWeakly-supervised Learning