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 2006.13566cs.CVcs.LG
收藏

DISK:使用策略梯度学习本地特征

DISK: Learning local features with policy gradient

École Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院);Google Research(谷歌研究院)

Michał J. Tyszkiewicz, Pascal Fua, Eduard Trulls

摘要:

由于稀疏关键点的选择和匹配所固有的离散性,局部特征框架很难以端到端的方式学习。我们引入了DISK(离散关键点),这是一种新方法,它通过利用强化学习(RL)的原理来克服这些障碍,优化端到端以获得大量正确的特征匹配。我们简单而富有表现力的概率模型使我们能够保持训练和推理机制的接近,同时保持足够好的收敛特性,以便从头开始可靠地进行训练。我们的特征可以非常密集地提取,同时保持区分性,挑战关于什么构成好的关键点的普遍假设,如图1所示,并在三个公共基准上提供最先进的结果。

英文摘要:

Local feature frameworks are difficult to learn in an end-to-end fashion, due to the discreteness inherent to the selection and matching of sparse keypoints. We introduce DISK (DIScrete Keypoints), a novel method that overcomes these obstacles by leveraging principles from Reinforcement Learning (RL), optimizing end-to-end for a high number of correct feature matches. Our simple yet expressive probabilistic model lets us keep the training and inference regimes close, while maintaining good enough convergence properties to reliably train from scratch. Our features can be extracted very densely while remaining discriminative, challenging commonly held assumptions about what constitutes a good keypoint, as showcased in Fig. 1, and deliver state-of-the-art results on three public benchmarks.

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。

↑