Text

Advanced Dropout : A Model-Free Methodology for Bayesian Dropout Optimization

Due to lack of data, overfitting ubiquitously exists in real-world applications of deep neural networks (DNNs). We propose advanced dropout, a model-free methodology, to mitigate overfitting and improve the performance of DNNs. The advanced dropout technique applies a model-free and easily implemented distribution with parametric prior, and adaptively adjusts dropout rate. Specifically, the distribution parameters are optimized by stochastic gradient variational Bayes in order to carry out an end-to-end training. We evaluate the effectiveness of the advanced dropout against nine dropout techniques on seven computer vision datasets (five small-scale datasets and two large-scale datasets) with various base models. The advanced dropout outperforms all the referred techniques on all the datasets. We further compare the effectiveness ratios and find that advanced dropout achieves the highest one on most cases. Next, we conduct a set of analysis of dropout rate characteristics, including convergence of the adaptive dropout rate, the learned distributions of dropout masks, and a comparison with dropout rate generation without an explicit distribution. In addition, the ability of overfitting prevention is evaluated and confirmed. Finally, we extend the application of the advanced dropout to uncertainty inference, network pruning, text classification, and regression. The proposed advanced dropout is also superior to the corresponding referred methods. Codes are available at https://github.com/PRIS-CV/AdvancedDropout .

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.44 No.9 Part 1 September 2022

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 4605-4625

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

DEEP NEURAL NETWORK
DROPOUT
MODEL-FREE DISTRIBUTION
BAYESIAN APPROXIMATION
STOCHASTIC GRADIENT VARIATIONAL BAYES

Info Detail Spesifik

10.1109/TPAMI.2021.3083089

Pernyataan Tanggungjawab

Jiyang Xie, Zhanyu Ma, Jianjun Lei, Guoqiang Zhang, Jing-Hao Xue, Zheng-Hua Tan, Jun Guo

Versi lain/terkait

Lampiran Berkas

Komentar