arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1407.5035cs.CV
收藏

LSDA:通过自适应的大规模检测

LSDA: Large Scale Detection Through Adaptation

UC Berkeley(加州大学伯克利分校);Tsinghua University(清华大学);UMass Lowell(马萨诸塞大学洛厄尔分校)

Judy Hoffman, Sergio Guadarrama, Eric Tzeng, Ronghang Hu, Jeff Donahue, Ross Girshick, Trevor Darrell, Kate Saenko

摘要:

缩放目标检测的一个主要挑战是难以获得大量类别的标记图像。最近,深度卷积神经网络(CNN)在对象分类基准测试中成为明显的赢家,部分原因是使用120万+标记的分类图像进行训练。不幸的是,这些标签中只有一小部分可用于检测任务。从搜索引擎收集大量的图像级标签比收集检测数据并用精确的边界框标记它要便宜得多,也容易得多。在本文中,我们提出了大规模检测通过自适应(LSDA),学习这两个任务之间的差异,并将此知识转移到分类器的类别没有限界框注释的数据,把它们变成检测器的算法。我们的方法有可能使成千上万的类别,缺乏限界框注释,但有大量的分类数据的检测。ImageNet LSVRC-2013检测挑战的评估证明了我们方法的有效性。该算法使我们能够通过使用ImageNet树中叶节点的可用分类数据来生成>7.6K的检测器。我们还演示了如何修改我们的架构,以产生一个快速的检测器(运行在2fps的7.6K检测器)。模型和软件可在

英文摘要:

A major challenge in scaling object detection is the difficulty of obtaining labeled images for large numbers of categories. Recently, deep convolutional neural networks (CNNs) have emerged as clear winners on object classification benchmarks, in part due to training with 1.2M+ labeled classification images. Unfortunately, only a small fraction of those labels are available for the detection task. It is much cheaper and easier to collect large quantities of image-level labels from search engines than it is to collect detection data and label it with precise bounding boxes. In this paper, we propose Large Scale Detection through Adaptation (LSDA), an algorithm which learns the difference between the two tasks and transfers this knowledge to classifiers for categories without bounding box annotated data, turning them into detectors. Our method has the potential to enable detection for the tens of thousands of categories that lack bounding box annotations, yet have plenty of classification data. Evaluation on the ImageNet LSVRC-2013 detection challenge demonstrates the efficacy of our approach. This algorithm enables us to produce a >7.6K detector by using available classification data from leaf nodes in the ImageNet tree. We additionally demonstrate how to modify our architecture to produce a fast detector (running at 2fps for the 7.6K detector). Models and software are available at

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。

↑