Scalable Deep Learning Logo Detection

Abstract

Existing logo detection methods usually consider a small number of logo classes and limited images per class with a strong assumption of requiring tedious object bounding box annotations, therefore not scalable to real-world dynamic applications. In this work, we tackle these challenges by exploring the webly data learning principle without the need for exhaustive manual labelling. Specifically, we propose a novel incremental learning approach, called Scalable Logo Self-co-Learning (SL^2), capable of automatically self-discovering informative training images from noisy web data for progressively improving model capability in a cross-model co-learning manner. Moreover, we introduce a very large (2,190,757 images of 194 logo classes) logo dataset "WebLogo-2M" by an automatic web data collection and processing method. Extensive comparative evaluations demonstrate the superiority of the proposed SL^2 method over the state-of-the-art strongly and weakly supervised detection models and contemporary webly data learning approaches.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
• Webly Supervised Learning of Convolutional Networks
• LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks
• DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer
• Cooperative Learning with Visual Attributes

Cited by in corpus (2)

• A Deep One-Shot Network for Query-based Logo Retrieval
• Recent Advances in Deep Learning for Object Detection