Solving the multiple instance problem with axis-parallel rectangles

1997/01/01 by Thomas G. Dietterich, Richard H. Lathrop, Tomás Lozano-Pérez +1 · 2,902 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Algorithm #Artificial intelligence #Computer science #Debugging #Feature (linguistics) #Feature vector #Image Retrieval and Classification Techniques #Machine learning #Object (grammar) #Pattern recognition (psychology) #Programming language #Rough Sets and Fuzzy Logic #Task (project management) #Theoretical computer science

paper · pdf · doi:10.1016/s0004-3702(96)00034-3

published in Artificial Intelligence 89(1-2), 31-71 (Elsevier BV)

openalex publication_date 1997/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Cited by

• Multiple instance classification: Review, taxonomy and comparative study
• Deep Learning Photo Processing for Periodontitis Screening
• EM-based iterations for multiple instance learning on a query-value model
• TellTale: Blending Multi-Instance LoRA Text Encoders and a Zero-Shot LLM Judge for Ambivalence/Hesitancy Recognition in Videos
• Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval
• Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions
• Latent Fisher Discriminant Analysis
• Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning
• DeltaMIL: Gated Memory Integration for Efficient and Discriminative Whole Slide Image Analysis
• WSSOD: A New Pipeline for Weakly- and Semi-Supervised Object Detection
• An Approach for Detection of Entities in Dynamic Media Contents
• milearn: A Python Package for Multi-Instance Machine Learning
• Structural Prognostic Event Modeling for Multimodal Cancer Survival Analysis
• Maximizing Cumulative User Engagement in Sequential Recommendation: An Online Optimization Perspective
• Attention-based Deep Multiple Instance Learning
• Hopfield Networks is All You Need
• MSA-MIL: A deep residual multiple instance learning model based on multi-scale annotation for classification and visualization of glomerular spikes
• Self-Paced Learning for Images of Antinuclear Antibodies
• Deep Multiple Instance Feature Learning via Variational Autoencoder
• A Vector Symbolic Approach to Multiple Instance Learning
• Surflex-Dock 2.1: Robust performance from ligand energetic modeling, ring flexibility, and knowledge-based search
• Multiple Instance Learning by Discriminative Training of Markov Networks
• Extreme Multi-label Classification from Aggregated Labels
• Synthetic Data Reveals Generalization Gaps in Correlated Multiple Instance Learning
• C-WSL: Count-guided Weakly Supervised Localization
• On the detection of Out-Of-Distribution samples in Multiple Instance Learning
• Object Detection in 20 Years: A Survey
• Sound event detection using weakly labeled dataset with stacked convolutional and recurrent neural network
• Nested Multiple Instance Learning in Modelling of HTTP network traffic
• AutoLoc: Weakly-supervised Temporal Action Localization
• A Review on Multi-Label Learning Algorithms
• Understanding Infographics through Textual and Visual Tag Prediction
• Deep Learning for Pneumothorax Detection and Localization in Chest Radiographs
• Constrained Convolutional Neural Networks for Weakly Supervised Segmentation
• A Multi-resolution Model for Histopathology Image Classification and Localization with Multiple Instance Learning
• Weakly Supervised Domain Detection
• Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding
• Annotation-Efficient Untrimmed Video Action Recognition
• A Real-time Global Inference Network for One-stage Referring Expression Comprehension
• Terabyte-scale Deep Multiple Instance Learning for Classification and\n Localization in Pathology
• Accounting for Dependencies in Deep Learning Based Multiple Instance Learning for Whole Slide Imaging
• Model-based Classification and Novelty Detection For Point Pattern Data
• Joint Analysis of Acoustic Scenes and Sound Events Based on Semi-Supervised Training of Sound Events With Partial Labels
• Sparse Network Inversion for Key Instance Detection in Multiple Instance Learning
• Synergistic Learning of Lung Lobe Segmentation and Hierarchical Multi-Instance Classification for Automated Severity Assessment of COVID-19 in CT Images
• Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification
• Enrich and Detect: Video Temporal Grounding with Multimodal LLMs
• Anomaly Detection with Inexact Labels
• Bandit Label Inference for Weakly Supervised Learning
• Grounding Referring Expressions in Images by Variational Context
• Noisy Labels for Weakly Supervised Gamma Hadron Classification
• Spatially Grounded Concept-Based Image Classification
• Learning Multi-level Deep Representations for Image Emotion Classification
• EfficientMIL: Efficient Linear-Complexity MIL Method for WSI Classification
• LABELING COPILOT: A Deep Research Agent for Automated Data Curation in Computer Vision
• A State-of-the-art Survey of Artificial Neural Networks for Whole-slide Image Analysis:from Popular Convolutional Neural Networks to Potential Visual Transformers
• AWARE-FX: An Auditable Knowledge-Guided AI System for Measuring Corporate Foreign-Exchange Hedging Disclosure
• NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection
• Modeling Precursors for Event Forecasting via Nested Multi-Instance Learning
• Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortion Detection
• Weakly-supervised Fingerspelling Recognition in British Sign Language Videos
• Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis
• Cluster-Level Sparse Multi-Instance Learning for Whole-Slide Images
• Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent
• Cluster-Based Learning from Weakly Labeled Bags in Digital Pathology
• Classification and Disease Localization in Histopathology Using Only Global Labels: A Weakly-Supervised Approach
• Multiplicative noise and heavy tails in stochastic optimization
• Specialized Decision Surface and Disentangled Feature for Weakly-Supervised Polyphonic Sound Event Detection
• Distant Supervision for Relation Extraction with Linear Attenuation Simulation and Non-IID Relevance Embedding
• Utilizing the Instability in Weakly Supervised Object Detection
• Multiple Instance Detection Network with Online Instance Classifier Refinement
• Dual-stream Maximum Self-attention Multi-instance Learning
• Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Images
• Increasing Information Extraction in Low-Signal Regimes via Multiple Instance Learning
• Multi-Task Learning for Interpretable Weakly Labelled Sound Event Detection
• Multi-instance Domain Adaptation for Vaccine Adverse Event Detection
• Evaluation of CNN-based Automatic Music Tagging Models
• Greedy Multiple Instance Learning via Codebook Learning and Nearest Neighbor Voting
• Multiple Instance Learning with the Optimal Sub-Pattern Assignment Metric
• Two-phase weakly supervised object detection with pseudo ground truth mining
• Weakly Supervised Representation Learning for Unsynchronized Audio-Visual Events
• Confidence-Constrained Maximum Entropy Framework for Learning from Multi-Instance Data
• Kernel Self-Attention in Deep Multiple Instance Learning
• Multiple Instance Reinforcement Learning for Efficient Weakly-Supervised Detection in Images
• Cross-Supervised Object Detection
• Complexity Guarantees for Polyak Steps with Momentum
• Learning Object Detection from Captions via Textual Scene Attributes
• Attention-Based Learning on Molecular Ensembles
• Neural relation extraction: a survey
• Document AI: Benchmarks, Models and Applications
• Domain Adaptations for Computer Vision Applications
• Introspective Classification with Convolutional Nets
• Histograms of Oriented Gradients for Landmine Detection in Ground-Penetrating Radar Data
• Distantly Supervised Relation Extraction in Federated Settings
• Ensemble of Part Detectors for Simultaneous Classification and Localization
• Artificial Intelligence for Pediatric Ophthalmology
• Automatic Assessment of the Design Quality of Python Programs with Personalized Feedback
• SGPMIL: Sparse Gaussian Process Multiple Instance Learning
• Fast Exact Inference for Recursive Cardinality Models
• CNN based Multi-Instance Multi-Task Learning for Syndrome Differentiation of Diabetic Patients
• Object Detection in 20 Years: A Survey
• Few-shot Classification as Multi-instance Verification: Effective Backbone-agnostic Transfer across Domains
• Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation
• One Size Fits Many: Column Bundle for Multi-X Learning
• Binary Classification from Positive Data with Skewed Confidence
• Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning
• FMaMIL: Frequency-Driven Mamba Multi-Instance Learning for Weakly Supervised Lesion Segmentation in Medical Images
• Learning Neural Networks with Two Nonlinear Layers in Polynomial Time
• End-to-End Learning of Visual Representations from Uncurated Instructional Videos
• Approximation capability of neural networks on spaces of probability measures and tree-structured domains
• Bag Reference Vector for Multi-instance Learning
• Look Closer to Ground Better: Weakly-Supervised Temporal Grounding of Sentence in Video
• Automatic CT Segmentation from Bounding Box Annotations using Convolutional Neural Networks
• A Convex Relaxation for Weakly Supervised Classifiers
• Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification
• Handcrafted Histological Transformer (H2T): Unsupervised representation of whole slide images
• Multiple-Instance Logistic Regression with LASSO Penalty
• Towards Reliable, Automated General Movement Assessment for Perinatal Stroke Screening in Infants Using Wearable Accelerometers
• Understanding the Role of Two-Sided Argumentation in Online Consumer Reviews: A Language-Based Perspective
• Towards Coarse and Fine-grained Multi-Graph Multi-Label Learning
• SparseConvMIL: Sparse Convolutional Context-Aware Multiple Instance Learning for Whole Slide Image Classification
• Adversarial Attack and Defense on Point Sets
• An algorithm for Left Atrial Thrombi detection using Transesophageal Echocardiography
• Learning Maximally Predictive Prototypes in Multiple Instance Learning
• Multi-Label Classifier Chains for Bird Sound
• Multiple Instance Hyperspectral Target Characterization
• Towards Robust Pattern Recognition: A Review
• Loss factorization, weakly supervised learning and label noise robustness
• Cross-Modal Retrieval with Implicit Concept Association
• MHAttnSurv: Multi-Head Attention for Survival Prediction Using Whole-Slide Pathology Images
• Logical settings for concept learning from incomplete examples in First Order Logic
• Generative Multiple-Instance Learning Models For Quantitative Electromyography
• Distributed Deep Forest and its Application to Automatic Detection of Cash-out Fraud
• Multiple-Instance Learning by Boosting Infinitely Many Shapelet-based Classifiers
• Weakly Supervised Classification Using Group-Level Labels
• Multi-instance Learning as Downstream Task of Self-Supervised Learning-based Pre-trained Model
• The Label Defines the Timescale: Trait-State Limits of Temporal-Aggregate Learning
• Inverse Graph Identification: Can We Identify Node Labels Given Graph Labels?
• Distance Measure Machines
• Self-paced Learning for Weakly Supervised Evidence Discovery in Multimedia Event Search
• Domain-Guided Task Decomposition with Self-Training for Detecting Personal Events in Social Media
• Object Instance Mining for Weakly Supervised Object Detection
• Exploiting Web Images for Weakly Supervised Object Detection
• Pushing the Boundaries of Boundary Detection using Deep Learning
• A bag-to-class divergence approach to multiple-instance learning
• AMIL: Adversarial Multi Instance Learning for Human Pose Estimation
• Multimodal Cancer Survival Analysis via Hypergraph Learning with Cross-Modality Rebalance
• EEG Representation Using Multi-instance Framework on The Manifold of Symmetric Positive Definite Matrices for EEG-based Computer Aided Diagnosis
• Convex Formulation of Multiple Instance Learning from Positive and Unlabeled Bags
• Label Distribution Learning
• (Machine) learning to do more with less
• Weakly Supervised Clustering by Exploiting Unique Class Count
• User Personalized Satisfaction Prediction via Multiple Instance Deep Learning
• Neural Inverse Knitting: From Images to Manufacturing Instructions
• Adaptive pooling operators for weakly labeled sound event detection
• A snapshot on nonstandard supervised learning problems: taxonomy, relationships and methods
• Cosine-similarity penalty to discriminate sound classes in weakly-supervised sound event detection
• Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels using Variational Auto-Encoder
• Reliable Shot Identification for Complex Event Detection via Visual-Semantic Embedding
• A Feature Selection Method for Multivariate Performance Measures
• Learning and Interpreting Multi-Multi-Instance Learning Networks
• A Multi-Dataset Benchmark of Multiple Instance Learning for 3D Neuroimage Classification
• On classification with bags, groups and sets
• Toward accurate breast cancer classification: A review of multi-modal machine learning approaches
• A convex method for classification of groups of examples
• Multi-view metric learning for multi-instance image classification
• How Effective Can Dropout Be in Multiple Instance Learning ?
• Deep learning for video classification and captioning
• Multiple instance learning for sequence data with across bag dependencies
• Attention-based Multi-instance Neural Network for Medical Diagnosis from Incomplete and Low Quality Data
• Classifying and segmenting microscopy images with deep multiple instance learning
• Deep Learning Approaches for Medical Imaging Under Varying Degrees of Label Availability: A Comprehensive Survey
• Training image classifiers using Semi-Weak Label Data
• On the Complexity of One-class SVM for Multiple Instance Learning
• Breast ultrasound image classification based on multiple-instance learning. [europepmc]
• Implementation of multiple-instance learning in drug activity prediction. [europepmc]
• Network-based prediction and knowledge mining of disease genes. [europepmc]
• Functional Networks of Highest-Connected Splice Isoforms: From The Chromosome 17 Human Proteome Project. [europepmc]
• Extracting microRNA-gene relations from biomedical literature using distant supervision. [europepmc]
• Machine learning for epigenetics and future medical applications. [europepmc]
• Tailored for Real-World: A Whole Slide Image Classification System Validated on Uncurated Multi-Site Data Emulating the Prospective Pathology Workload. [europepmc]
• Weakly-supervised learning for lung carcinoma classification using deep learning. [europepmc]
• Deep learning-enabled breast cancer hormonal receptor status determination from base-level H&E stains. [europepmc]
• Deep Learning Predicts Underlying Features on Pathology Images with Therapeutic Relevance for Breast and Gastric Cancer. [europepmc]
• Deep learning-enabled medical computer vision. [europepmc]
• Interpretable prediction of necrotizing enterocolitis from machine learning analysis of premature infant stool microbiota. [europepmc]
• DeepLION: Deep Multi-Instance Learning Improves the Prediction of Cancer-Associated T Cell Receptors for Accurate Cancer Detection. [europepmc]
• Classification of Breast Cancer Histopathological Images Using DenseNet and Transfer Learning. [europepmc]
• Detection of m6A from direct RNA sequencing using a multiple instance learning framework. [europepmc]
• Explainable AI identifies diagnostic cells of genetic AML subtypes. [europepmc]
• Learning to predict RNA sequence expressions from whole slide images with applications for search and classification. [europepmc]
• Machine learning classification of placental villous infarction, perivillous fibrin deposition, and intervillous thrombus. [europepmc]
• Histopathology images predict multi-omics aberrations and prognoses in colorectal cancer patients. [europepmc]
• TMBserval: a statistical explainable learning model reveals weighted tumor mutation burden better categorizing therapeutic benefits. [europepmc]
• Multiple-instance learning of somatic mutations for the classification of tumour type and the prediction of microsatellite status. [europepmc]
• Automating General Movements Assessment with quantitative deep learning to facilitate early screening of cerebral palsy. [europepmc]
• Teacher-student collaborated multiple instance learning for pan-cancer PDL1 expression prediction from histopathology slides. [europepmc]
• AI-based histopathology image analysis reveals a distinct subset of endometrial cancers. [europepmc]
• Multimodal deep learning approaches for precision oncology: a comprehensive review. [europepmc]