CANet : class-agnostic segmentation networks with iterative refinement and attentive few-shot learning

• Main Authors: Zhang, Chi, Lin, Guosheng, Liu, Fayao, Yao, Rui, Shen, Chunhua
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2020
• Subjects: Engineering::Computer science and engineering; Retrieval; Segmentation
• Online Access: https://hdl.handle.net/10356/144391
• Institution: Nanyang Technological University

Recent progress in semantic segmentation is driven by deep Convolutional Neural Networks and large-scale labeled image datasets. However, data labeling for pixel-wise segmentation is tedious and costly. Moreover, a trained model can only make predictions within a set of pre-defined classes. In this...