Abstract | ||
---|---|---|
Convolutional neural networks(CNNs) have achieved overwhelming success in image recognition. For all the architectures of CNNs, the low-level features extracted from the input is essential for the whole model because it determines the upper bound of accuracy. However, due to the random initialization and end-to-end training mechanism, there is no guarantee that the learned convolutional layer is an excellent low-level feature extractor. Thus, we propose Gabor binary layer(GBL) as a more efficient alternative to the first convolutional layer in CNNs. The design principle of GBL is motivated by local Gabor binary patterns. The GBL is comprised of a module of pre-defined Gabor convolutional filters in different orientations and shapes, and a module of fixed randomly generated binary convolutional filters to encode the Gabor features. By replacing the first layer of Resnet-56, Resnet-110, and LBCNN with the GBL, we achieve better performances on SVHN, CIFAR-10 and CIFAR-100 than that of the original models. Results show that the proposed GBL outperforms the standard convolutional layer for extracting low-level features, and thus the GBL can easily improve the performances of CNNs on image recognition. |
Year | Venue | Keywords |
---|---|---|
2018 | 2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Gabor, low-level features, convolutional network, image recognition |
Field | DocType | ISSN |
ENCODE,Convolutional code,Pattern recognition,Convolutional neural network,Upper and lower bounds,Computer science,Feature extraction,Extractor,Artificial intelligence,Initialization,Binary number | Conference | 1522-4880 |
Citations | PageRank | References |
1 | 0.35 | 0 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chenzhi Jiang | 1 | 1 | 0.35 |
Jianbo Su | 2 | 231 | 38.20 |