Hierarchical Deep Learning Architecture for 10K Objects Classification

Abstract

Evolution of visual object recognition architectures based on Convolutional Neural Networks & Convolutional Deep Belief Networks paradigms has revolutionized artificial Vision Science. These architectures extract & learn the real world hierarchical visual features utilizing supervised & unsupervised learning approaches respectively. Both the approaches yet cannot scale up realistically to provide recognition for a very large number of objects as high as 10K. We propose a two level hierarchical deep learning architecture inspired by divide & conquer principle that decomposes the large scale recognition architecture into root & leaf level model architectures. Each of the root & leaf level models is trained exclusively to provide superior results than possible by any 1-level deep learning architecture prevalent today. The proposed architecture classifies objects in two steps. In the first step the root level model classifies the object in a high level category. In the second step, the leaf level recognition model for the recognized high level category is selected among all the leaf models. This leaf level model is presented with the same input object image which classifies it in a specific category. Also we propose a blend of leaf level models trained with either supervised or unsupervised learning approaches. Unsupervised learning is suitable whenever labelled data is scarce for the specific leaf level models. Currently the training of leaf level models is in progress; where we have trained 25 out of the total 47 leaf level models as of now. We have trained the leaf models with the best case top-5 error rate of 3.2% on the validation data set for the particular leaf models. Also we demonstrate that the validation error of the leaf level models saturates towards the above mentioned accuracy as the number of epochs are increased to more than sixty. The top-5 error rate for the entire two-level architecture needs to be computed in conjunction with the error rates of root & all the leaf models. The realization of this two level visual recognition architecture will greatly enhance the accuracy of the large scale object recognition scenarios demanded by the use cases as diverse as drone vision, augmented reality, retail, image search & retrieval, robotic navigation, targeted advertisements etc.

Penerapan Multi-Label Image Classification Menggunakan Metode Convolutional Neural Network (CNN) Untuk Sortir Botol Minuman

“…[3][4][5] Multi label image classification tentunya akan sangat relevan jika diterapkan pada pengolahan gambar digital di kehidupan sehari hari, karena di dalam satu gambar biasanya tidak hanya terdapat satu label saja tapi bisa lebih dari dua label sekaligus. [6]…”

Hierarchical Classification of Very Small Objects: Application to the Detection of Arthropod Species

“…Hierarchical classification has been used in deep learning for the handling of large datasets with numerous classes [11]- [13]. For classification tasks, Katole et al achieved 3.2 % error rate on the ImageNet 10K dataset [11] that features over 10,000 classes using hierarchical classification [12]. Hierarchical classification was also used for detection tasks on ImageNet.…”

Convolutional Neural Network Technology in Endoscopic Imaging: Artificial Intelligence for Endoscopy

“…35 A well-trained CNN consists of a hierarchy of information such as an edge, a corner, a part of an object, and a structure of an object in image classification. 36 A single CNN architecture consists of a series of convolutional layers, pooling layers, followed by a fully connected layer. The main purpose of a convolutional layer is to extract learnable features such as characteristic local motifs from images.…”