Browse SoTA > Methodology > Multiple Instance Learning

# Multiple Instance Learning Edit

58 papers with code · Methodology

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.

# Benchmarks Add a Result

No evaluation results yet. Help compare methods by submit evaluation metrics.

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

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.

916

# Attention-based Deep Multiple Instance Learning

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

892

# Real-world Anomaly Detection in Surveillance Videos

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.

312

# PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

9 Jul 2018ppengtang/oicr

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.

195

# Multiple Instance Detection Network with Online Instance Classifier Refinement

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.

195

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

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

164

# Weakly labelled audioset tagging with attention neural networks

We bridge the connection between attention neural networks and multiple instance learning (MIL) methods, and propose decision-level and feature-level attention neural networks for audio tagging.

144

# Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection

Remarkably, we obtain the frame-level AUC score of 82. 12% on UCF-Crime.

143

# Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval

In this work, we introduce Polysemous Instance Embedding Networks (PIE-Nets) that compute multiple and diverse representations of an instance by combining global context with locally-guided features via multi-head self-attention and residual learning.

79

# Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networks

23 Sep 2020utayao/Atten_Deep_MIL

We evaluated our methods on two large cancer whole slide images datasets and our results suggest that the proposed approach is more effective and suitable for large datasets and has better interpretability in locating important patterns and features that contribute to accurate cancer survival predictions.

77