Search Results for author: Qi Xu

Found 6 papers, 1 papers with code

Deep Auto-encoder with Neural Response

no code implementations30 Nov 2021 Xuming Ran, Jie Zhang, Ziyuan Ye, Haiyan Wu, Qi Xu, Huihui Zhou, Quanying Liu

In this study, we propose an integrated framework called Deep Autoencoder with Neural Response (DAE-NR), which incorporates information from ANN and the visual cortex to achieve better image reconstruction performance and higher neural representation similarity between biological and artificial neurons.

Image Reconstruction

Two Sample Unconditional Quantile Effect

no code implementations20 May 2021 Atsushi Inoue, Tong Li, Qi Xu

This paper proposes a new framework to evaluate unconditional quantile effects (UQE) in a data combination model.

Bigeminal Priors Variational auto-encoder

no code implementations5 Oct 2020 Xuming Ran, Mingkun Xu, Qi Xu, Huihui Zhou, Quanying Liu

The likelihood-based generative models have been reported to be highly robust to the out-of-distribution (OOD) inputs and can be a detector by assuming that the model assigns higher likelihoods to the samples from the in-distribution (ID) dataset than an OOD dataset.

Detecting Out-of-distribution Samples via Variational Auto-encoder with Reliable Uncertainty Estimation

no code implementations16 Jul 2020 Xuming Ran, Mingkun Xu, Lingrui Mei, Qi Xu, Quanying Liu

To address this problem, a reliable uncertainty estimation is considered to be critical for in-depth understanding of OOD inputs.

Anomaly Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.