Search Results for author:
Found 5 papers, 1 papers with code
Sequential Embedding Induced Text Clustering, a Non-parametric Bayesian Approach
In this paper, the documents are modeled as the joint of bags of words, sequential features and word embeddings.
Dynamic Importance Sampling for Anytime Bounds of the Partition Function
Our algorithm combines and generalizes recent work on anytime search and probabilistic bounds of the partition function.
Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification
Inspired by the success of using deep convolutional features for natural image analysis and multi-instance learning (MIL) for labeling a set of instances/patches, we propose end-to-end trained deep multi-instance networks for mass classification based on whole mammogram without the aforementioned ROIs.
Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification
Inspired by the success of using deep convolutional features for natural image analysis and multi-instance learning for labeling a set of instances/patches, we propose end-to-end trained deep multi-instance networks for mass classification based on whole mammogram without the aforementioned costly need to annotate the training data.
Novelty Detection Under Multi-Instance Multi-Label Framework
Contrary to the common assumption in MIML that each instance in a bag belongs to one of the known classes, in novelty detection, we focus on the scenario where bags may contain novel-class instances.
