DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer

7 Oct 2015  ·  Forrest N. Iandola, Anting Shen, Peter Gao, Kurt Keutzer ·

Recently, there has been a flurry of industrial activity around logo recognition, such as Ditto's service for marketers to track their brands in user-generated images, and LogoGrab's mobile app platform for logo recognition. However, relatively little academic or open-source logo recognition progress has been made in the last four years. Meanwhile, deep convolutional neural networks (DCNNs) have revolutionized a broad range of object recognition applications. In this work, we apply DCNNs to logo recognition. We propose several DCNN architectures, with which we surpass published state-of-art accuracy on a popular logo recognition dataset.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Object Detection FlickrLogos-32 DeepLogo (VGG) MAP 74.4 # 2
Object Detection FlickrLogos-32 DeepLogo (AlexNet) MAP 73.5 # 3
Image Classification FlickrLogos-32 DeepLogo (GoogLeNet-GP) Accuracy 89.6 # 3

Methods


No methods listed for this paper. Add relevant methods here