Enhanced representation and multi-task learning for image annotation
Enhanced representation and multi-task learning for image annotation
复制标题
DOI：
10.1016/j.cviu.2012.09.006
复制
发表时间：
2013-05-01
影响因子：
4.5
通讯作者：
Kawanabe, Motoaki
中科院分区：
文献类型：
--
作者：
Binder, Alexander;Samek, Wojciech;Kawanabe, Motoaki
在本文中，我们提出了一种新的有偏随机抽样策略的词袋模型的图像表示。我们评估其对一组语义概念的特征属性和排名质量的影响，并表明它提高了图像注释任务中分类器的性能，并增加了内核和标签之间的相关性。作为第二个贡献，我们提出了一种称为输出核多任务学习（MTL）的方法，通过类之间的信息传输来提高排名性能。输出核MTL的主要优点是它允许任务之间的不对称信息传输，并可以扩展到数千张图像的训练集。我们给出了一个理论解释的方法，并表明源任务的目标任务的学习贡献是语义一致的。这两种策略都在ImageCLEF PhotoAnnotation数据集上进行了评估。我们使用MTL方法的最佳视觉结果在ImageCLEF 2011 PhotoAnnotation Challenge的纯视觉提交中根据平均精度（mAP）排名第一。我们的多模式提交作品在同一比赛的所有提交作品中获得了mAP的第一名。(C)2012 Elsevier Inc. All rights reserved.
In this paper we propose a novel biased random sampling strategy for image representation in Bag-of-Words models. We evaluate its impact on the feature properties and the ranking quality for a set of semantic concepts and show that it improves performance of classifiers in image annotation tasks and increases the correlation between kernels and labels. As second contribution we propose a method called Output Kernel Multi-Task Learning (MTL) to improve ranking performance by transfer information between classes. The main advantages of output kernel MTL are that it permits asymmetric information transfer between tasks and scales to training sets of several thousand images. We give a theoretical interpretation of the method and show that the learned contributions of source tasks to target tasks are semantically consistent. Both strategies are evaluated on the ImageCLEF PhotoAnnotation dataset.Our best visual result which used the MTL method was ranked first according to mean Average Precision (mAP) within the purely visual submissions in the ImageCLEF 2011 PhotoAnnotation Challenge. Our multi-modal submission achieved the first rank by mAP among all submissions in the same competition. (C) 2012 Elsevier Inc. All rights reserved.