arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1412.0100cs.CVcs.LG
收藏

基于多实例强化学习的图像弱监督检测

Multiple Instance Reinforcement Learning for Efficient Weakly-Supervised Detection in Images

Institute of Mathematics of the Romanian Academy of Science(罗马尼亚科学院数学研究所);University of Toronto(多伦多大学);Lund University(隆德大学)

Stefan Mathe, Cristian Sminchisescu

摘要:

最先进的视觉识别和检测系统越来越依赖于大量的训练数据和复杂的分类器。因此,手动注释数据集和将运行时间保持在实际应用可接受的水平上变得越来越昂贵。在本文中,我们提出了两个解决方案来解决这些问题。首先,我们引入了一种弱监督的,基于分割的方法来学习准确的检测器和图像分类器从弱监督信号,只提供近似的约束目标定位。我们使用人类视觉搜索模式作为我们的训练信号,说明了我们的系统在静态图像中的动作检测问题(Pascal VOC Actions 2012)。其次,从人类视觉系统的扫视和注视操作原理的启发,我们使用强化学习技术来训练有效的搜索模型进行检测。我们的顺序方法是弱监督和一般的(它不需要眼球运动),找到最佳的搜索策略为任何给定的检测置信度函数,并实现性能类似于穷举滑动窗口搜索的一小部分,其计算成本。

英文摘要:

State-of-the-art visual recognition and detection systems increasingly rely on large amounts of training data and complex classifiers. Therefore it becomes increasingly expensive both to manually annotate datasets and to keep running times at levels acceptable for practical applications. In this paper, we propose two solutions to address these issues. First, we introduce a weakly supervised, segmentation-based approach to learn accurate detectors and image classifiers from weak supervisory signals that provide only approximate constraints on target localization. We illustrate our system on the problem of action detection in static images (Pascal VOC Actions 2012), using human visual search patterns as our training signal. Second, inspired from the saccade-and-fixate operating principle of the human visual system, we use reinforcement learning techniques to train efficient search models for detection. Our sequential method is weakly supervised and general (it does not require eye movements), finds optimal search strategies for any given detection confidence function and achieves performance similar to exhaustive sliding window search at a fraction of its computational cost.

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。

↑