Multiple Instance Learning

85 papers with code • 0 benchmarks • 7 datasets

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

Greatest papers with code

Attention-based Deep Multiple Instance Learning

ml-jku/hopfield-layers ICML 2018

Multiple instance learning (MIL) is a variation of supervised learning where a single class label is assigned to a bag of instances.

Aerial Scene Classification Multiple Instance Learning

Multiple Instance Learning for Efficient Sequential Data Classification on Resource-constrained Devices

Microsoft/EdgeML NeurIPS 2018

We propose a method, EMI-RNN, that exploits these observations by using a multiple instance learning formulation along with an early prediction technique to learn a model that achieves better accuracy compared to baseline models, while simultaneously reducing computation by a large fraction.

General Classification Multiple Instance Learning +2

Real-world Anomaly Detection in Surveillance Videos

WaqasSultani/AnomalyDetectionCVPR2018 CVPR 2018

To avoid annotating the anomalous segments or clips in training videos, which is very time consuming, we propose to learn anomaly through the deep multiple instance ranking framework by leveraging weakly labeled training videos, i. e. the training labels (anomalous or normal) are at video-level instead of clip-level.

Activity Recognition Anomaly Detection In Surveillance Videos +2

Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks

lucidrains/perceiver-pytorch ICLR 2019

Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances.

3D Shape Recognition Few-Shot Image Classification +1

PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

ppengtang/oicr 9 Jul 2018

The iterative instance classifier refinement is implemented online using multiple streams in convolutional neural networks, where the first is an MIL network and the others are for instance classifier refinement supervised by the preceding one.

Multiple Instance Learning Object Recognition +1

Multiple Instance Detection Network with Online Instance Classifier Refinement

ppengtang/oicr CVPR 2017

We propose a novel online instance classifier refinement algorithm to integrate MIL and the instance classifier refinement procedure into a single deep network, and train the network end-to-end with only image-level supervision, i. e., without object location information.

Multiple Instance Learning Object Recognition +1

Towards Precise End-to-end Weakly Supervised Object Detection Network

ppengtang/pcl.pytorch ICCV 2019

It is challenging for weakly supervised object detection network to precisely predict the positions of the objects, since there are no instance-level category annotations.

Multiple Instance Learning Weakly Supervised Object Detection

Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images

mahmoodlab/CLAM 20 Apr 2020

CLAM is a general-purpose and adaptable method that can be used for a variety of different computational pathology tasks in both clinical and research settings.

Domain Adaptation Multiple Instance Learning +2