Instance Learning

Instance learning (IL) addresses classification problems where labels are assigned to bags of instances, rather than individual data points, a common scenario in medical imaging and other fields with limited annotations. Current research focuses on improving IL model architectures, such as incorporating transformers and attention mechanisms to better capture instance relationships and mitigate biases stemming from spurious correlations between bag features and labels, while also exploring probabilistic and self-supervised approaches for improved robustness and interpretability. The development of effective IL methods holds significant promise for advancing weakly supervised learning across diverse applications, particularly in areas where obtaining fine-grained labels is costly or impractical.

Papers

April 20, 2022

Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction
Tiancheng Lin, Hongteng Xu, Canqian Yang, Yi Xu
Instance Learning Causal Intervention Instance Selection

March 24, 2022

Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection
Hitesh Sapkota, Qi Yu
Video Anomaly Detection Instance Learning Video Anomaly Object Proposal Robust Anomaly Detection

March 15, 2022

Breast Cancer Molecular Subtypes Prediction on Pathological Images with Discriminative Patch Selecting and Multi-Instance Learning
Hong Liu, Wen-Dong Xu, Zi-Hao Shang, Xiang-Dong Wang, Hai-Yan Zhou, Ke-Wen Ma, Huan Zhou, Jia-Lin Qi, Jia-Rui Jiang, Li-Lan Tan, Hui-Min Zeng, Hui-Juan Cai, Kuan-Song Wang, Yue-Liang Qian
Pathology Image Instance Learning Patch Level Cancer Subtype Intra Tumoral Genetic Heterogeneity Molecular Subtypes

March 9, 2022

Attention-effective multiple instance learning on weakly stem cell colony segmentation
Novanto Yudistira, Muthu Subash Kavitha, Jeny Rajan, Takio Kurita
Multiple Instance Learning Weakly Supervised Cell Segmentation Instance Learning Multiple Instance

February 25, 2022

Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization
Weijia Zhang, Xuanhui Zhang, Han-Wen Deng, Min-Ling Zhang
Distribution Generalization Instance Learning Multiple Instance Instance Prediction Instance Level Causal

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

Instance Learning

Papers

Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction

Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection

Breast Cancer Molecular Subtypes Prediction on Pathological Images with Discriminative Patch Selecting and Multi-Instance Learning

Attention-effective multiple instance learning on weakly stem cell colony segmentation

Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization

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