Deep Multiple Instance

Deep Multiple Instance Learning (MIL) addresses the challenge of classifying collections of data (bags) where only bag-level labels are available, not individual instance labels. Current research focuses on improving MIL's accuracy and interpretability through techniques like attention mechanisms (e.g., smooth attention, distance-aware self-attention, probabilistic attention using Gaussian Processes), hierarchical models, and incorporating external information such as eye-tracking data. This approach is particularly valuable in domains like medical image analysis and natural language processing where obtaining instance-level labels is costly or impractical, enabling the development of more efficient and robust diagnostic tools and information extraction systems.

Papers

July 18, 2023

Smooth Attention for Deep Multiple Instance Learning: Application to CT Intracranial Hemorrhage Detection
Yunan Wu, Francisco M. Castro-Macías, Pablo Morales-Álvarez, Rafael Molina, Aggelos K. Katsaggelos
Application Proficiency Multiple Instance Learning Instance Query Human Instance Instance Level Label Deep Multiple Instance Intracranial Hemorrhage Detection Smooth Attention

May 30, 2023

Hierarchical Multi-Instance Multi-Label Learning for Detecting Propaganda Techniques
Anni Chen, Bhuwan Dhingra
Multi Label Auxiliary Classifier Propaganda Content Propaganda Detection Rhetorical Structure Hierarchical Label Propaganda Technique Deep Multiple Instance

May 17, 2023

Deep Multiple Instance Learning with Distance-Aware Self-Attention
Georg Wölflein, Lucie Charlotte Magister, Pietro Liò, David J. Harrison, Ognjen Arandjelović
Self Attention Multiple Instance Learning Spatial Information Deep Multiple Instance Relative Positional

April 25, 2023

Eye tracking guided deep multiple instance learning with dual cross-attention for fundus disease detection
Hongyang Jiang, Jingqi Huang, Chen Tang, Xiaoqing Zhang, Mengdi Gao, Jiang Liu
Multiple Instance Learning Eye Tracking Early Disease Detection Deep Multiple Instance Dual Cross Attention Gaze Control

February 8, 2023

Probabilistic Attention based on Gaussian Processes for Deep Multiple Instance Learning
Arne Schmidt, Pablo Morales-Álvarez, Rafael Molina
Gaussian Process Multiple Instance Learning Instance Learning Deep Multiple Instance Gaussian Attention

July 26, 2022

Tree edit distance for hierarchical data compatible with HMIL paradigm
Břetislav Šopík, Tomáš Strenáčik
Raw Data Structured Data Multidimensional Array Storage Strategy Hierarchical Datasets Edit Distance Deep Multiple Instance Tree Edit Distance

June 29, 2022

Deep Multiple Instance Learning For Forecasting Stock Trends Using Financial News
Yiqi Deng, Siu Ming Yiu
Multiple Instance Learning Stock Trend Trend Analysis Financial News Deep Multiple Instance

June 12, 2022

Balancing Bias and Variance for Active Weakly Supervised Learning
Hitesh Sapkota, Qi Yu
Weakly Supervised Learning Variance Information Balanced Approach Robust Bayesian Deep Multiple Instance Instance Prediction

June 9, 2022

Multiple Instance Learning for Digital Pathology: A Review on the State-of-the-Art, Limitations & Future Potential
Michael Gadermayr, Maximilian Tschuchnig
Deep Neural Network Full Potential State of the Art Multiple Instance Learning Digital Pathology Fundamental Limitation Deep Multiple Instance

February 3, 2022

Oral cancer detection and interpretation: Deep multiple instance learning versus conventional deep single instance learning
Nadezhda Koriakina, Nataša Sladoje, Vladimir Bašić, Joakim Lindblad
Abstract Interpretation Instance Learning Oral Cancer Cytology Image Deep Multiple Instance

December 17, 2021

Interpretable and Interactive Deep Multiple Instance Learning for Dental Caries Classification in Bitewing X-rays
Benjamin Bergner, Csaba Rohrer, Aiham Taleb, Martha Duchrau, Guilherme De Leon, Jonas Almeida Rodrigues, Falk Schwendicke, Joachim Krois, Christoph Lippert
Image Level Label Interpretable Way Instance Learning Segmentation Label Deep Multiple Instance

Deep Multiple Instance

Papers

Smooth Attention for Deep Multiple Instance Learning: Application to CT Intracranial Hemorrhage Detection

Hierarchical Multi-Instance Multi-Label Learning for Detecting Propaganda Techniques

Deep Multiple Instance Learning with Distance-Aware Self-Attention

Eye tracking guided deep multiple instance learning with dual cross-attention for fundus disease detection

Probabilistic Attention based on Gaussian Processes for Deep Multiple Instance Learning

Tree edit distance for hierarchical data compatible with HMIL paradigm

Deep Multiple Instance Learning For Forecasting Stock Trends Using Financial News

Balancing Bias and Variance for Active Weakly Supervised Learning

Multiple Instance Learning for Digital Pathology: A Review on the State-of-the-Art, Limitations & Future Potential

Oral cancer detection and interpretation: Deep multiple instance learning versus conventional deep single instance learning

Interpretable and Interactive Deep Multiple Instance Learning for Dental Caries Classification in Bitewing X-rays