arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.08698cs.CVcs.AI
收藏

基于预训练原型分类器的端到端细化

End-to-End Refinement Guided by Pre-trained Prototypical Classifier

Cornell University(康奈尔大学);Oxford University(牛津大学);Princeton University(普林斯顿大学);Purdue University(普渡大学);California Institute of Technology(加州理工学院)

Junwen Bai, Zihang Lai, Runzhe Yang, Yexiang Xue, John Gregoire, Carla Gomes

摘要:

许多现实世界的任务涉及从满足背景或先验知识的数据中识别模式。在材料发现等领域,由于原始实验数据中的缺陷和偏差,X射线衍射图(XRD)的识别通常需要大量的手工工作,以找到与理想理论相类似的精细相。因此,期望利用模拟的理论数据来自动精炼原始XRD。我们提出了模仿细化,一种新的方法来完善不完美的输入模式,指导下的预先训练的分类器,结合先验知识从模拟的理论数据,这样的细化模式模仿理想的数据。分类器在理想的模拟数据上进行训练以分类模式,并学习嵌入空间,其中每个类由原型表示。细化器学习通过小的修改来细化不完美的模式,使得它们的嵌入更接近相应的原型。我们表明,精炼机可以在监督和无监督的方式进行培训。我们进一步说明了所提出的方法的有效性,定性和定量的数字细化任务和X射线衍射图案细化任务的材料发现。

英文摘要:

Many real-world tasks involve identifying patterns from data satisfying background or prior knowledge. In domains like materials discovery, due to the flaws and biases in raw experimental data, the identification of X-ray diffraction patterns (XRD) often requires a huge amount of manual work in finding refined phases that are similar to the ideal theoretical ones. Automatically refining the raw XRDs utilizing the simulated theoretical data is thus desirable. We propose imitation refinement, a novel approach to refine imperfect input patterns, guided by a pre-trained classifier incorporating prior knowledge from simulated theoretical data, such that the refined patterns imitate the ideal data. The classifier is trained on the ideal simulated data to classify patterns and learns an embedding space where each class is represented by a prototype. The refiner learns to refine the imperfect patterns with small modifications, such that their embeddings are closer to the corresponding prototypes. We show that the refiner can be trained in both supervised and unsupervised fashions. We further illustrate the effectiveness of the proposed approach both qualitatively and quantitatively in a digit refinement task and an X-ray diffraction pattern refinement task in materials discovery.

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。

↑