Few-shot deep model of waste classification based on model agnostic meta learning

Bo Feng; Ren Kun; Qingyang Tao; Honggui Han

doi:10.1117/12.2601132

9 October 2021 Few-shot deep model of waste classification based on model agnostic meta learning

Bo Feng, Ren Kun, Qingyang Tao, Honggui Han

Proceedings Volume 11897, Optoelectronic Imaging and Multimedia Technology VIII; 118970Q (2021) https://doi.org/10.1117/12.2601132
Event: SPIE/COS Photonics Asia, 2021, Nantong, JS, China

Conference Poster

Abstract

Waste classification based on deep neural networks is up against the dataset deficiency. However, that is too expensive and time-consuming for collecting and labeling waste samples. We proposed an improved ResNet-18 model based on Model Agnostic Meta-Learning (MAML) to improve classification accuracy with a few-shot waste classification dataset. the feature extraction part of the improved model includes a convolution layer and four residual blocks; the classification part of the improved model includes a max-pooling layer and three fully connected layers. Moreover, GroupNorm is adopted to reduce the impact of different feature distributions normalization on the classification accuracy. With initial parameters from the MAML training on the Mini-ImageNet dataset, the model improve accuracy only with one training iteration results on few waste samples. The experiments verified the effectiveness of our model on the Mini-ImageNet dataset and a few-shot waste classification dataset

Citation Download Citation

Bo Feng, Ren Kun, Qingyang Tao, and Honggui Han "Few-shot deep model of waste classification based on model agnostic meta learning", Proc. SPIE 11897, Optoelectronic Imaging and Multimedia Technology VIII, 118970Q (9 October 2021); https://doi.org/10.1117/12.2601132

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available