arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.05708cs.CV
收藏

基于动态特征选择的鲁棒图像匹配

Robust Image Matching By Dynamic Feature Selection

New York University(纽约大学);New York University Abu Dhabi(纽约大学阿布扎比分校)

Hao Huang, Jianchun Chen, Xiang Li, Lingjing Wang, Yi Fang

摘要:

估计图像之间的密集对应关系是一个长期存在的图像理解任务。最近的工作引入了卷积神经网络(CNN)来提取高级特征图并通过特征匹配找到对应关系。然而,高级特征图的空间分辨率较低,因此不足以提供准确和细粒度的特征来区分类内变化以进行对应匹配。为了解决这个问题,我们生成强大的功能,通过动态选择功能在不同的尺度。为了解决特征选择中的两个关键问题,即,我们将特征选择过程构造为一个连续的马尔可夫决策过程(MDP),并引入了一种使用强化学习(RL)的最优选择策略。我们定义了一个用于图像匹配的RL环境,其中每个单独的动作要么需要新的功能,要么通过引用匹配分数来终止选择情节。深度神经网络被整合到我们的方法中,并被训练用于决策。实验结果表明,我们的方法实现了相当/优越的性能与国家的最先进的方法在三个基准测试,证明了我们的特征选择策略的有效性。

英文摘要:

Estimating dense correspondences between images is a long-standing image under-standing task. Recent works introduce convolutional neural networks (CNNs) to extract high-level feature maps and find correspondences through feature matching. However,high-level feature maps are in low spatial resolution and therefore insufficient to provide accurate and fine-grained features to distinguish intra-class variations for correspondence matching. To address this problem, we generate robust features by dynamically selecting features at different scales. To resolve two critical issues in feature selection,i.e.,how many and which scales of features to be selected, we frame the feature selection process as a sequential Markov decision-making process (MDP) and introduce an optimal selection strategy using reinforcement learning (RL). We define an RL environment for image matching in which each individual action either requires new features or terminates the selection episode by referring a matching score. Deep neural networks are incorporated into our method and trained for decision making. Experimental results show that our method achieves comparable/superior performance with state-of-the-art methods on three benchmarks, demonstrating the effectiveness of our feature selection strategy.

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。

↑