Anytime Recognition with Routing Convolutional Networks.

IEEE Transactions on Pattern Analysis and Machine Intelligence(2021)

引用 19|浏览127
暂无评分
摘要
Achieving an automatic trade-off between accuracy and efficiency for a single deep neural network is highly desired in time-sensitive computer vision applications. To achieve anytime prediction, existing methods only embed fixed exits to neural networks and make the predictions with the fixed exits for all the samples (refer to the “latest-all” strategy). However, it is observed that the latest ex...
更多
查看译文
关键词
Routing,Neural networks,Task analysis,Benchmark testing,Computational modeling,Reinforcement learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要