2018/05/11 by Lu Yu, Yu, Lu, Yongmei Cheng +3
Biochemistry, Genetics and Molecular Biology · Computer Science · Neuroscience · Psychology · #Color perception and design #Olfactory and Sensory Function Studies #cs.CV #melanin and skin pigmentation
paper · pdf · doi:10.48550/arxiv.1805.04385
Accepted at ICPR2018
arxiv created 2018/05/11 · arxiv updated 2018/05/14
The majority of existing color naming methods focuses on the eleven basic color terms of the English language. However, in many applications, different sets of color names are used for the accurate description of objects. Labeling data to learn these domain-specific color names is an expensive and laborious task. Therefore, in this article we aim to learn color names from weakly labeled data. For this purpose, we add an attention branch to the color naming network. The attention branch is used to modulate the pixel-wise color naming predictions of the network. In experiments, we illustrate that the attention branch correctly identifies the relevant regions. Furthermore, we show that our method obtains state-of-the-art results for pixel-wise and image-wise classification on the EBAY dataset and is able to learn color names for various domains.