Sort by: Year Popularity Relevance

BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation

, , , , ,  - 2020

Instance segmentation is one of the fundamental vision tasks. Recently, fully convolutional instance segmentation methods have drawn much attention as they are often simpler and more efficient than two-stage approaches like Mask R-CNN. To date, almost all such approaches fall behind the two-stage Mask R-CNN method in mask precision when models ha...


Identifying Critical Neurons in ANN Architectures using Mixed Integer Programming

, ,  - 2020

We introduce a novel approach to optimize the architecture of deep neural networks by identifying critical neurons and removing non-critical ones. The proposed approach utilizes a mixed integer programming (MIP) formulation of neural models which includes a continuous importance score computed for each neuron in the network. The optimization in MIP...


PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning

,  - 2020

The recent success of deep neural networks (DNNs) for function approximation in reinforcement learning has triggered the development of Deep Reinforcement Learning (DRL) algorithms in various fields, such as robotics, computer games, natural language processing, computer vision, sensing systems, and wireless networking. Unfortunately, DNNs suffer...


Schema2QA: Answering Complex Queries on the Structured Web with a Neural Model

, , ,  - 2020

Virtual assistants have proprietary third-party skill platforms; they train and own the voice interface to websites based on their submitted skill information. This paper proposes Schema2QA, an open-source toolkit that leverages the Schema.org markup found in many websites to automatically build skills. Schema2QA has several advantages: (1) Schem...


Learning Generative Models using Denoising Density Estimators

, , , ,  - 2020

Learning generative probabilistic models that can estimate the continuous density given a set of samples, and that can sample from that density, is one of the fundamental challenges in unsupervised machine learning. In this paper we introduce a new approach to obtain such models based on what we call denoising density estimators (DDEs). A DDE is ...


Learning Contextualized Document Representations for Healthcare Answer Retrieval

, , , ,  - 2020

We present Contextual Discourse Vectors (CDV), a distributed document representation for efficient answer retrieval from long healthcare documents. Our approach is based on structured query tuples of entities and aspects from free text and medical taxonomies. Our model leverages a dual encoder architecture with hierarchical LSTM layers and multi-...


Inductive Document Network Embedding with Topic-Word Attention

, ,  - 2020

Document network embedding aims at learning representations for a structured text corpus i.e. when documents are linked to each other. Recent algorithms extend network embedding approaches by incorporating the text content associated with the nodes in their formulations. In most cases, it is hard to interpret the learned representations. Moreover...


Bridging Text and Video: A Universal Multimodal Transformer for Video-Audio Scene-Aware Dialog

, , , , ,  - 2020

Audio-Visual Scene-Aware Dialog (AVSD) is a task to generate responses when chatting about a given video, which is organized as a track of the 8th Dialog System Technology Challenge (DSTC8). To solve the task, we propose a universal multimodal transformer and introduce the multi-task learning method to learn joint representations among different ...


Pix2Pix-based Stain-to-Stain Translation: A Solution for Robust Stain Normalization in Histopathology Images Analysis

,  - 2020

The diagnosis of cancer is mainly performed by visual analysis of the pathologists, through examining the morphology of the tissue slices and the spatial arrangement of the cells. If the microscopic image of a specimen is not stained, it will look colorless and textured. Therefore, chemical staining is required to create contrast and help identif...


Segmented Graph-Bert for Graph Instance Modeling

 - 2020

In graph instance representation learning, both the diverse graph instance sizes and the graph node orderless property have been the major obstacles that render existing representation learning models fail to work. In this paper, we will examine the effectiveness of GRAPH-BERT on graph instance representation learning, which was designed for node...