CRL: Class Representative Learning for Image Classification

Abstract

Building robust and real-time classifiers with diverse datasets are one of the most significant challenges to deep learning researchers. It is because there is a considerable gap between a model built with training (seen) data and real (unseen) data in applications. Recent works including Zero-Shot Learning (ZSL), have attempted to deal with this problem of overcoming the apparent gap through transfer learning. In this paper, we propose a novel model, called Class Representative Learning Model (CRL), that can be especially effective in image classification influenced by ZSL. In the CRL model, first, the learning step is to build class representatives to represent classes in datasets by aggregating prominent features extracted from a Convolutional Neural Network (CNN). Second, the inferencing step in CRL is to match between the class representatives and new data. The proposed CRL model demonstrated superior performance compared to the current state-of-the-art research in ZSL and mobile deep learning. The proposed CRL model has been implemented and evaluated in a parallel environment, using Apache Spark, for both distributed learning and recognition. An extensive experimental study on the benchmark datasets, ImageNet-1K, CalTech-101, CalTech-256, CIFAR-100, shows that CRL can build a class distribution model with drastic improvement in learning and recognition performance without sacrificing accuracy compared to the state-of-the-art performances in image classification.

arXiv comment15 pages, Table 8, Figure 6

References in corpus (18)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distributed Representations of Words and Phrases and their Compositionality
• Auto-Encoding Variational Bayes
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Prototypical Networks for Few-shot Learning
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Wide Residual Networks
• Semi-Supervised Learning with Deep Generative Models
• An Analysis of Deep Neural Network Models for Practical Applications
• Label-Embedding for Image Classification
• Zero-Shot Learning by Convex Combination of Semantic Embeddings
• Deep Residual Networks with Exponential Linear Unit
• Universal representations:The missing link between faces, text, planktons, and cat breeds
• Rethinking ImageNet Pre-training
• Zero-Shot Learning via Class-Conditioned Deep Generative Models
• Vocabulary-informed Zero-shot and Open-set Learning
• Episode-based Prototype Generating Network for Zero-Shot Learning