Hierarchical deep convolutional neural network for image classification

US10387773B2 · kind B2 · utility

Assignee

• eBay Inc. · US

Inventors

• Zhicheng Yan · Palo Alto, US
• Robinson Piramuthu · Oakland, US
• Vignesh Jagadeesh · Cupertino, US
• Wei Di · San Jose, US
• Dennis M. DeCoste · Tustin, US

Key dates

• Filing date: Dec 23, 2014
• Grant date: Aug 20, 2019
• Expiry date: Jul 14, 2036

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/084
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Hierarchical branching deep convolutional neural networks (HD-CNNs) improve existing convolutional neural network (CNN) technology. In a HD-CNN, classes that can be easily distinguished are classified in a higher layer coarse category CNN, while the most difficult classifications are done on lower layer fine category CNNs. Multinomial logistic loss and a novel temporal sparsity penalty may be used in HD-CNN training. The use of multinomial logistic loss and a temporal sparsity penalty causes each branching component to deal with distinct subsets of categories.