A Hierarchical Matcher using Local Classifier Chains

TL;DR

This paper introduces a hierarchical matcher called LCC-CNN that enhances visual recognition accuracy by combining a global neural network with local binary classifiers in a chain structure, avoiding error propagation.

Contribution

It proposes a novel hierarchical matcher using local classifier chains built on label similarities, improving recognition performance without altering the global network architecture.

Findings

Achieves higher accuracy than global-only methods.

Improves face recognition accuracy by 1% on UHDB31.

Enhances image and character recognition performance.

Abstract

This paper focuses on improving the performance of current convolutional neural networks in visual recognition without changing the network architecture. A hierarchical matcher is proposed that builds chains of local binary neural networks after one global neural network over all the class labels, named as Local Classifier Chains based Convolutional Neural Network (LCC-CNN). The signature of each sample as two components: global component based on the global network; local component based on local binary networks. The local networks are built based on label pairs created by a similarity matrix and confusion matrix. During matching, each sample travels through one global network and a chain of local networks to obtain its final matching to avoid error propagation. The proposed matcher has been evaluated with image recognition, character recognition and face recognition datasets. The experimental results indicate that the proposed matcher achieves better performance when compared with methods using only a global deep network. Compared with the UR2D system, the accuracy is improved significantly by 1% and 0.17% on the UHDB31 dataset and the IJB-A dataset, respectively.