Facial image retrieval plays a significant role in forensic investigations where an untrained witness tries to identify a suspect from a massive pool of images. However, due to the difficulties in describing human facial appearances verbally and dire
ctly, people naturally tend to depict by referring to well-known existing images and comparing specific areas of faces with them and it is also challenging to provide complete comparison at each time. Therefore, we propose an end-to-end framework to retrieve facial images with relevance feedback progressively provided by the witness, enabling an exploitation of history information during multiple rounds and an interactive and iterative approach to retrieving the mental image. With no need of any extra annotations, our model can be applied at the cost of a little response effort. We experiment on texttt{CelebA} and evaluate the performance by ranking percentile and achieve 99% under the best setting. Since this topic remains little explored to the best of our knowledge, we hope our work can serve as a stepping stone for further research.
Conventional uncertainty quantification methods usually lacks the capability of dealing with high-dimensional problems due to the curse of dimensionality. This paper presents a semi-supervised learning framework for dimension reduction and reliabilit
y analysis. An autoencoder is first adopted for mapping the high-dimensional space into a low-dimensional latent space, which contains a distinguishable failure surface. Then a deep feedforward neural network (DFN) is utilized to learn the mapping relationship and reconstruct the latent space, while the Gaussian process (GP) modeling technique is used to build the surrogate model of the transformed limit state function. During the training process of the DFN, the discrepancy between the actual and reconstructed latent space is minimized through semi-supervised learning for ensuring the accuracy. Both labeled and unlabeled samples are utilized for defining the loss function of the DFN. Evolutionary algorithm is adopted to train the DFN, then the Monte Carlo simulation method is used for uncertainty quantification and reliability analysis based on the proposed framework. The effectiveness is demonstrated through a mathematical example.
We study degree-theoretic properties of reals that are not random with respect to any continuous probability measure (NCR). To this end, we introduce a family of generalized Hausdorff measures based on the iterates of the dissipation function of a co
ntinuous measure and study the effective nullsets given by the corresponding Solovay tests. We introduce two constructions that preserve non-randomness with respect to a given continuous measure. This enables us to prove the existence of NCR reals in a number of Turing degrees. In particular, we show that every $Delta^0_2$-degree contains an NCR element.
Atmospheric muons are one of the main backgrounds for current Water- and Ice-Cherenkov neutrino telescopes designed to detect astrophysical neutrinos. The inclusive fluxes of atmospheric muons and neutrinos from hadronic interactions of cosmic rays h
ave been extensively studied with Monte Carlo and cascade equation methods, for example, CORSIKA and MCEq. However, the muons that are pair produced in electromagnetic interaction of high energy photons are quantitatively not well understood. We present new simulation results and assess the model dependencies of the high-energy atmospheric muon flux including those from electromagnetic interactions, using a new numerical electromagnetic cascade equation solver EmCa that can be easily coupled with the hadronic solver MCEq. Both codes are in active development with the particular aim to become part of the next generation CORSIKA 8 air shower simulation package. The combination of EmCa and MCEq accounts for material effects that have not been previously included in most of the available codes. Hence, the influence of these effects on the air showers will also be briefly discussed.
