Guided Networks for Few-Shot Image Segmentation and Fully Connected CRFs

Electronics

Jian Lian¹  Yuanjie Zheng²  Kun Zhang²  Weikuan Jia²  Xin Chen²  Xiaobo Deng³ 

[1] Department of Electrical Engineering and Information Technology, Shandong University of Science and Technology, Jinan 250031, China;School of Information Science and Engineering, Shandong Normal University, Jinan 250358, China;Shandong Key Laboratory for Testing Technology of Material, Chemical Safety, Jinan 250102, China;

关键词: few-shot learning;    image segmentation;    convolutional neural networks;    conditional random fields;   

DOI  :  10.3390/electronics9091508

来源: DOAJ

【 摘 要 】

The goal of the few-shot learning method is to learn quickly from a low-data regime. Structured output tasks like segmentation are challenging for few-shot learning, due to their being high-dimensional and statistically dependent. For this problem, we propose improved guided networks and combine them with a fully connected conditional random field (CRF). The guided network extracts task representations from annotated support images through feature fusion to do fast, accurate inference on new unannotated query images. By bringing together few-shot learning methods and fully connected CRFs, our method can do accurate object segmentation by overcoming poor localization properties of deep convolutional neural networks and can quickly updating tasks, without further optimization, when faced with new data. Our guided network is at the forefront of accuracy for the terms of annotation volume and time.

【 授权许可】

Unknown