no code implementations • 29 Nov 2018 • Tiehang Duan, Qi Lou, Sargur N. Srihari, Xiaohui Xie
In this paper, the documents are modeled as the joint of bags of words, sequential features and word embeddings.
no code implementations • NeurIPS 2017 • Qi Lou, Rina Dechter, Alexander T. Ihler
Our algorithm combines and generalizes recent work on anytime search and probabilistic bounds of the partition function.
1 code implementation • 23 May 2017 • Wentao Zhu, Qi Lou, Yeeleng Scott Vang, Xiaohui Xie
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.
no code implementations • 18 Dec 2016 • Wentao Zhu, Qi Lou, Yeeleng Scott Vang, Xiaohui Xie
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.
no code implementations • 25 Nov 2013 • Qi Lou, Raviv Raich, Forrest Briggs, Xiaoli Z. Fern
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.