Automatic annotation of visual deep neural networks

TL;DR

This paper presents an automatic annotation system for visual deep neural networks using natural language processing, achieving around 90% accuracy in labeling models' application fields, thus aiding developers in model selection.

Contribution

It introduces a novel automatic labeling method for visual neural networks based on semantic analysis, improving model understanding and retrieval.

Findings

Achieved 90% correct annotation rate in top conferences

Demonstrated effectiveness of NLP-based automatic labeling

Facilitated faster model understanding for developers

Abstract

Computer vision is widely used in the fields of driverless, face recognition and 3D reconstruction as a technology to help or replace human eye perception images or multidimensional data through computers. Nowadays, with the development and application of deep neural networks, the models of deep neural networks proposed for computer vision are becoming more and more abundant, and developers will use the already trained models on the way to solve problems, and need to consult the relevant documents to understand the use of the model. The class model, which creates the need to quickly and accurately find the relevant models that you need. The automatic annotation method of visual depth neural network proposed in this paper is based on natural language processing technology such as semantic analysis, which realizes automatic labeling of model application fields. In the three top international conferences on computer vision: ICCV, CVPR and ECCV, the average correct rate of application of the papers of 72 papers reached 90%, indicating the effectiveness of the automatic labeling system.