arXiv 1807.019642018-07cs.CV

开放式徽标检测挑战

Open Logo Detection Challenge

Queen Mary University of London（伦敦玛丽女王大学）；Vision Semantics Limited（视觉语义有限公司）

Hang Su, Xiatian Zhu, Shaogang Gong

备注：: Accepted by BMVC 2018. The QMUL-OpenLogo benchmark is publicly available at: qmul-openlogo.github.io

摘要：

现有的徽标检测基准通过假设具有针对每个类的细粒度限界框注释的大训练数据可用于模型训练来考虑人工部署场景。这样的假设在现实的标志检测场景中通常是无效的，在现实的标志检测场景中，新的标志类逐渐出现，并且需要以很少或没有预算来检测用于详尽地标记每个新类的细粒度训练数据。因此，现有的基准测试无法评估真实和开放部署中徽标检测方法的真实性能。在这项工作中，我们介绍了一个更现实和具有挑战性的标志检测设置，称为开放标志检测。具体地说，这个新设置假设仅在一小部分徽标类上进行细粒度标记，而其余类没有标记的训练数据来模拟开放部署。我们进一步创建了一个开放的标志检测基准，称为OpenLogo，以促进对这一新挑战的调查。OpenLogo包含来自352个徽标类的27，083个图像，通过聚合/精炼7个现有数据集并建立开放徽标检测评估协议构建。为了应对这一挑战，我们提出了一种上下文对抗学习（CAL）方法，用于在不同的背景上下文下合成具有连贯徽标实例外观的训练数据，以更有效地优化当代深度学习检测模型。实验表明，CAL的性能优势，现有的国家的最先进的替代方法上更现实和更具挑战性的OpenLogo基准。

英文摘要：

Existing logo detection benchmarks consider artificial deployment scenarios by assuming that large training data with fine-grained bounding box annotations for each class are available for model training. Such assumptions are often invalid in realistic logo detection scenarios where new logo classes come progressively and require to be detected with little or none budget for exhaustively labelling fine-grained training data for every new class. Existing benchmarks are thus unable to evaluate the true performance of a logo detection method in realistic and open deployments. In this work, we introduce a more realistic and challenging logo detection setting, called Open Logo Detection. Specifically, this new setting assumes fine-grained labelling only on a small proportion of logo classes whilst the remaining classes have no labelled training data to simulate the open deployment. We further create an open logo detection benchmark, called OpenLogo,to promote the investigation of this new challenge. OpenLogo contains 27,083 images from 352 logo classes, built by aggregating/refining 7 existing datasets and establishing an open logo detection evaluation protocol. To address this challenge, we propose a Context Adversarial Learning (CAL) approach to synthesising training data with coherent logo instance appearance against diverse background context for enabling more effective optimisation of contemporary deep learning detection models. Experiments show the performance advantage of CAL over existing state-of-the-art alternative methods on the more realistic and challenging OpenLogo benchmark.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

摘要：

英文摘要：

相关论文