Hierarchical Convolutional Deep Learning in Computer Vision

58 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep Learning: Methods and Applications (2014, methodology): “thesis on the topic of deep learning for computer vision (Zeiler, 2014).”
Deep learning for visual understanding (2017, unknown): “There are three main advantages of the convolution operation [36]: 1) the weight sharing mechanism in the same feature map reduces the number of parameters; 2) local connectivity learns correlations among neighboring pixels; 3) invariance to the location of the object.”
Mixed Pooling for Convolutional Neural Networks (2014, methodology): “In this work, similar to [10], a novel type of pooling method, termed as mixed pooling, is proposed in order to boost the regularization performance for training larger CNN models.”