Attention-based Convolutional Neural Network for Computer Vision Color Constancy (CROSBI ID 682802)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Koščević, Karlo ; Subašić, Marko ; Lončarić, Sven
engleski
Attention-based Convolutional Neural Network for Computer Vision Color Constancy
Achieving color constancy is an important part of image preprocessing pipeline of contemporary digital cameras. Its goal is to eliminate the influence of the illumination color on the colors of the objects in the image scene. State-of-the- art results have been achieved with learning- based methods, especially when the deep learning approaches have been applied. Several methods that are combining local patches for global illumination estimations exist. However, in this paper, a new convolutional neural network architecture is proposed. It is trained to look for the regions, i.e., patches in the image where the most useful information about the scene illumination is contained. This is achieved with the attention mechanism stacked on top of the pretrained convolutional neural network. Additionally, the common problem of the lack of data in color constancy benchmark datasets is alleviated utilizing the stage-wise training. Experimental results show that the proposed approach achieves competitive results.
Attention mechanism, color constancy, convolutional neural networks, deep learning, illumination estimation, image enhancement
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
372-377.
2019.
objavljeno
10.1109/ISPA.2019.8868806
Podaci o matičnoj publikaciji
Proceedings of the 11th International Symposium on Image and Signal Processing and Analysis
Podaci o skupu
11th International Symposium on Image and Signal Processing and Analysis (ISPA 2019)
predavanje
23.09.2019-25.09.2019
Dubrovnik, Hrvatska