DeepFuse Neural Networks

摘要：

　　Generally,pre-trained backbone convolutional models for image classification are directly used as default backbone model for other tasks including detection and segmentation,so as to avoid training a new model from scratch.However,segmentation and detection frameworks need combining low-level and high-level features to boost performance.In this paper,we point out and prove that a simple fusion of low-level and high-level features is insufficient and defined an operation named DeepFuse as a generic family of building blocks for feature fusion.This building block can be plugged into any existing architectures and prevent overfitting effectively for region-level and pixel-level tasks.Based on the Mask R-CNN framework,we achieved a 1.9 AP improvement on the validation set of cityscape and a 1.7 AP improvement on the test set by the use of DeepFuse operation.

关键词： Region-level task Pixel-level task Feature fusion DeepFuse Mask RCNN

作者: Xiu Li Rujiao Long Kun Jin

作者单位: Department of Automation Tsinghua University Shenzhen,Guangdong,China

会议类型: 国际会议

会议名称: 2019国图灵大会(ACM Turing Celebration conference-China 2019 )

会议地点: 成都

会议语种:英文

页码: 231-235

在线出版日期: 2019-05-17（万方平台首次上网日期，不代表论文的发表时间）