arXiv subjects

Mindren Lu

Publications and source records attributed to Mindren Lu.

2 recordsLinked to original sources

arXiv2020

MosAIc: Finding Artistic Connections across Culture with Conditional Image Retrieval

We introduce MosAIc, an interactive web app that allows users to find pairs of semantically related artworks that span different cultures, media, and millennia. To create this application, we introduce Conditional Image Retrieval (CIR) which combines visual similarity search with user supplied filters or "conditions". This technique allows one to find pairs of similar images that span distinct subsets of the image corpus. We provide a generic way to adapt existing image retrieval data-structures to this new domain and provide theoretical bounds on our approach's efficiency. To quantify the performance of CIR systems, we introduce new datasets for evaluating CIR methods and show that CIR performs non-parametric style transfer. Finally, we demonstrate that our CIR data-structures can identify "blind spots" in Generative Adversarial Networks (GAN) where they fail to properly model the true data distribution.

cs.LG↗

arXiv2019

A Deep Learning Model for Atomic Structures Prediction Using X-ray Absorption Spectroscopic Data

A deep neural network (DNN) model consisting of two hidden layers was proposed for predicting the immediate environments of specific atoms based on X-ray absorption near-edge spectra (XANES). The output layer of the DNN can be adjusted to form a classifier or regressor, to predict the local and overall coordination environments, respectively. Using Li3FeO3.5 as a model system, it was demonstrated that the prediction accuracy of the DNN classifier is higher than 98%, and the predictions of the DNN regressor also showed notable agreement with the ground truth. Therefore, despite its simplicity, this DNN architecture can be expected to be generally capable of predicting the structural properties of various systems. Fine tuning of the hyperparameters, bias-variance tradeoff, and strategies to enrich the versatility of the model were also discussed.

physics.comp-ph↗