Removing Out - Of - Distribution Samples on Classification Task

• 발행기관: 한국스마트미디어학회
• 저자명: Thanh-Vu Dang Hoang-Trong Vo 유광현(Gwang-Hyun Yu) 이주환(Ju-Hwan Lee) Huy-Toan Nguyen 김진영(Jin-Young Kim)
• 간행물 정보: 『스마트미디어저널』Vol9, No.3, 80~89쪽, 전체 10쪽
• 주제분류: 공학 > 컴퓨터학
• 파일형태: PDF
• 발행일자: 2020.09.30

영문 초록

Out - of - distribution (OOD) samples are frequently encountered when deploying a classification model in plenty of real-world machine learning-based applications. Those samples are normally sampling far away from the training distribution, but many classifiers still assign them high reliability to belong to one of the training categories. In this study, we address the problem of removing OOD examples by estimating marginal density estimation using variational autoencoder (VAE). We also investigate other proper methods, such as temperature scaling, Gaussian discrimination analysis, and label smoothing. We use Chonnam National University (CNU) weeds dataset as the in - distribution dataset and CIFAR-10, CalTeach as the OOD datasets. Quantitative results show that the proposed framework can reject the OOD test samples with a suitable threshold.

목차

Ⅰ. INTRODUCTION

Ⅱ. PRELIMINARIES

Ⅲ. PROPOSED FRAMEWORK

Ⅳ. EXPERIMENT

Ⅴ. CONCLUSION

REFERENCES

키워드

Out of distribution detection Classification Neural Networks Statistical Modeling