ZipNet: ZFNet-level Accuracy with 48 x Fewer Parameters

檔案

本條目沒有附加檔案。

日期

2018-01-01

期刊名稱

2018 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (IEEE VCIP)

摘要

With the introduction of Convolutional Neural Networks, models for image classification achieve higher classification accuracy. Based on the pattern of the design of CNN architectures, increasing the number of layers equates to a higher classification accuracy, but also increases the number of parameters and model size. This negatively affects the model training time, processing time, and memory requirement. We develop ZipNet, a CNN architecture with a higher classification accuracy than ZFNet, the winner of ILSVRC 2013, but with 48.5x smaller model size and 48.7x fewer parameters. The classification accuracy of ZipNet is higher than the performance of ZFNet and SqueezeNet on all configurations of the Caltech-256 dataset with varying number of training examples.

所屬典藏

會議論文
顯示完整詮釋資料 統計資料