SOTAVerified

Multiple Instance Learning

Multiple Instance Learning is a type of weakly supervised learning algorithm where training data is arranged in bags, where each bag contains a set of instances $X=\{x_1,x_2, \ldots,x_M\}$, and there is one single label $Y$ per bag, $Y\in\{0, 1\}$ in the case of a binary classification problem. It is assumed that individual labels $y_1, y_2,\ldots, y_M$ exist for the instances within a bag, but they are unknown during training. In the standard Multiple Instance assumption, a bag is considered negative if all its instances are negative. On the other hand, a bag is positive, if at least one instance in the bag is positive.

Source: Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 601–650 of 744 papers

TitleStatusHype
C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object DetectionCode0
Deep Learning Under the Microscope: Improving the Interpretability of Medical Imaging Neural Networks—0
Weakly Supervised Object Detection with Segmentation Collaboration—0
Thyroid Cancer Malignancy Prediction From Whole Slide Cytopathology Images—0
InfoMask: Masked Variational Latent Representation to Localize Chest Disease—0
Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly DetectionCode0
Root Identification in Minirhizotron Imagery with Multiple Instance LearningCode0
Multi-Instance Learning for End-to-End Knowledge Base Question Answering—0
Pornographic Image Recognition via Weighted Multiple Instance Learning—0
Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification—0
Disease Detection in Weakly Annotated Volumetric Medical Images using a Convolutional LSTM Network—0
Multiple Instance Learning for ECG Risk Stratification—0
Multiple Instance Learning for Efficient Sequential Data Classification on Resource-constrained Devices—0
A Multiclass Multiple Instance Learning Method with Exact LikelihoodCode0
Multiple-Instance Learning by Boosting Infinitely Many Shapelet-based Classifiers—0
Identify, locate and separate: Audio-visual object extraction in large video collections using weak supervision—0
Learning to quantify emphysema extent: What labels do we need?—0
Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly SupervisedCode0
Deep Multiple Instance Learning for Airplane Detection in High Resolution Imagery—0
TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection—0
Spatio-Temporal Instance Learning: Action Tubes from Class Supervision—0
Deep Multiple Instance Feature Learning via Variational Autoencoder—0
Characterizing multiple instance datasets—0
A convex method for classification of groups of examples—0
Multiple Instance Learning for Heterogeneous Images: Training a CNN for Histopathology—0
W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection—0
Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos—0
Pointly-Supervised Action Localization—0
Training Medical Image Analysis Systems like Radiologists—0
Reliable counting of weakly labeled concepts by a single spiking neuron model—0
Terabyte-scale Deep Multiple Instance Learning for Classification and Localization in Pathology—0
Weakly-Supervised Video Object Grounding from Text by Loss Weighting and Object Interaction—0
Learning Pretopological Spaces to Model Complex Propagation Phenomena: A Multiple Instance Learning Approach Based on a Logical Modeling—0
Adaptive pooling operators for weakly labeled sound event detectionCode0
Weakly Supervised Representation Learning for Unsynchronized Audio-Visual Events—0
Cross-Modal Retrieval with Implicit Concept Association—0
Video Representation Learning Using Discriminative Pooling—0
Towards Universal Representation for Unseen Action Recognition—0
Deep Multiple Instance Learning for Zero-shot Image TaggingCode0
Multiple Instance Choquet Integral Classifier Fusion and Regression for Remote Sensing ApplicationsCode0
A bag-to-class divergence approach to multiple-instance learningCode0
Mixed Supervised Object Detection with Robust Objectness Transfer—0
Classification and Disease Localization in Histopathology Using Only Global Labels: A Weakly-Supervised Approach—0
Grounding Referring Expressions in Images by Variational ContextCode0
Learning Pain from Action Unit Combinations: A Weakly Supervised Approach via Multiple Instance Learning—0
Multimodal Visual Concept Learning with Weakly Supervised TechniquesCode0
Multiple Instance Learning Networks for Fine-Grained Sentiment AnalysisCode0
Multiple Instance Curriculum Learning for Weakly Supervised Object Detection—0
Multiple-Instance, Cascaded Classification for Keyword Spotting in Narrow-Band Audio—0
pyLEMMINGS: Large Margin Multiple Instance Classification and Ranking for Bioinformatics Applications—0
Show:102550
← PrevPage 13 of 15Next →
All datasetsCAMELYON16TCGAElephantMusk v1Musk v2

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Snuffy (DINO Exhaustive)AUC0.99—Unverified
2Snuffy (SimCLR Exhaustive)AUC0.97—Unverified
3CAMILAUC0.96—Unverified
4CAMIL (CAMIL-L)AUC0.95—Unverified
5CAMIL (CAMIL-G)AUC0.95—Unverified
6DTFD-MIL (AFS)AUC0.95—Unverified
7DTFD-MIL (MAS)AUC0.95—Unverified
8DTFD-MIL (MaxMinS)AUC0.94—Unverified
9TransMILAUC0.93—Unverified
10DSMIL-LCAUC0.92—Unverified
#ModelMetricClaimedVerifiedStatus
1DTFD-MIL (MAS)AUC0.96—Unverified
2DTFD-MIL (AFS)ACC0.95—Unverified
3Snuffy (SimCLR Exhaustive)ACC0.95—Unverified
4DSMIL-LCACC0.93—Unverified
5DSMILACC0.92—Unverified
6DTFD-MIL (MaxMinS)ACC0.89—Unverified
7TransMILACC0.88—Unverified
8DTFD-MIL (MaxS)ACC0.87—Unverified
#ModelMetricClaimedVerifiedStatus
1SnuffyAUC0.97—Unverified
2DSMILACC0.93—Unverified
#ModelMetricClaimedVerifiedStatus
1SnuffyACC0.96—Unverified
2DSMILACC0.95—Unverified
#ModelMetricClaimedVerifiedStatus
1DSMILACC0.93—Unverified
2SnuffyACC0.79—Unverified