arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1606.03558cs.CV
收藏

通用通信网

Universal Correspondence Network

Stanford University(斯坦福大学);NEC Laboratories America, Inc.(美国NEC实验室)

Christopher B. Choy, JunYoung Gwak, Silvio Savarese, Manmohan Chandraker

摘要:

我们提出了一个深度学习框架,用于准确的视觉对应,并证明了其有效性的几何和语义匹配,跨越刚性运动到类内形状或外观变化。与之前基于CNN的方法优化代理补丁相似性目标相比,我们使用深度度量学习来直接学习保留几何或语义相似性的特征空间。我们的全卷积架构以及新颖的对应对比损失允许通过有效重用计算来实现更快的训练,通过使用每个图像对的数千个示例来实现精确的梯度计算,以及使用$O(n)$前馈传递对$n$关键点进行更快的测试,而不是使用$O(n^2)$进行典型的补丁相似性方法。我们提出了一个卷积空间Transformer来模仿SIFT等传统特征中的补丁归一化,这被证明可以显着提高跨类内形状变化的语义对应的准确性。在KITTI、PASCAL和CUB-2011数据集上进行的大量实验表明,我们的特征比使用手工构造或学习特征的先前作品具有显着优势。

英文摘要:

We present a deep learning framework for accurate visual correspondences and demonstrate its effectiveness for both geometric and semantic matching, spanning across rigid motions to intra-class shape or appearance variations. In contrast to previous CNN-based approaches that optimize a surrogate patch similarity objective, we use deep metric learning to directly learn a feature space that preserves either geometric or semantic similarity. Our fully convolutional architecture, along with a novel correspondence contrastive loss allows faster training by effective reuse of computations, accurate gradient computation through the use of thousands of examples per image pair and faster testing with $O(n)$ feed forward passes for $n$ keypoints, instead of $O(n^2)$ for typical patch similarity methods. We propose a convolutional spatial transformer to mimic patch normalization in traditional features like SIFT, which is shown to dramatically boost accuracy for semantic correspondences across intra-class shape variations. Extensive experiments on KITTI, PASCAL, and CUB-2011 datasets demonstrate the significant advantages of our features over prior works that use either hand-constructed or learned features.

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。

↑