文献类型：期刊文献

英文题名：Adaptive adversarial prototyping network for few-shot prototypical translation*

作者：Phaphuangwittayakul, Aniwat[1,6];Ying, Fangli[2];Guo, Yi[1,3,4];Santisookrat, Surachai[5]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Dept Comp Sci & Engn, State Key Lab Bioreactor Engn, Shanghai 200237, Peoples R China;[3]Natl Engn Lab Big Data Distribut & Exchange Techno, Business Intelligence & Visualizat Res Ctr, Shanghai 200436, Peoples R China;[4]Shanghai Engn Res Ctr Big Data & Internet Audience, Shanghai 200072, Peoples R China;[5]Chiang Mai Univ, Innovat Coll North, 169 Moo3, Chiang Mai 50230, Thailand;[6]Chiang Mai Univ, Int Coll Digital Innovat, Chiang Mai 50200, Thailand

年份：2023

卷号：94

外文期刊名：JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION

收录：;EI(收录号：20232114125806);WOS:【SCI-EXPANDED(收录号:WOS:001001915200001)】；

基金：This research is financially supported by National Key Research and Development Program of China (No. 2020YFA0907800) ; Partially Supported by Open Funding Project of the State Key Laboratory of Bioreactor Engineering, East China University of Science and Technology, Shanghai, China; is also supported by The National Key Research and Development Program of China (grant number 2018YFC0807105) and Science and Technology Committee of Shanghai Municipality (STCSM) (under grant numbers 17DZ1101003, 18511106602 and 18DZ2252300) ; and International College of Digital Innovation (ICDI) , Chiang Mai University, Thailand.

语种：英文

外文关键词：Prototyping network; Few-shot image translation; Meta-learning; Generative adversarial network

摘要：Translating multiple real-world source images to a single prototypical image is a challenging problem. Notably, these source images belong to unseen categories that did not exist during model training. We address this problem by proposing an adaptive adversarial prototype network (AAPN) and enhancing existing one-shot classification techniques. To overcome the limitations that traditional works cannot extract samples from novel categories, our method tends to solve the image translation task of unseen categories through a metalearner. We train the model in an adversarial learning manner and introduce a style encoder to guide the model with an initial target style. The encoded style latent code enhances the performance of the network with conditional target style images. The AAPN outperforms the state-of-the-art methods in one-shot classification of brand logo dataset and achieves the competitive accuracy in the traffic sign dataset. Additionally, our model improves the visual quality of the reconstructed prototypes in unseen categories. Based on the qualitative and quantitative analysis, the effectiveness of our model for few-shot classification and generation is demonstrated.