arXiv subjects

Kaili Wang

Publications and source records attributed to Kaili Wang.

22 records · Page 2Linked to original sources

arXiv2021

Multiple Exemplars-based Hallucinationfor Face Super-resolution and Editing

Given a really low-resolution input image of a face (say 16x16 or 8x8 pixels), the goal of this paper is to reconstruct a high-resolution version thereof. This, by itself, is an ill-posed problem, as the high-frequency information is missing in the low-resolution input and needs to be hallucinated, based on prior knowledge about the image content. Rather than relying on a generic face prior, in this paper, we explore the use of a set of exemplars, i.e. other high-resolution images of the same person. These guide the neural network as we condition the output on them. Multiple exemplars work better than a single one. To combine the information from multiple exemplars effectively, we introduce a pixel-wise weight generation module. Besides standard face super-resolution, our method allows to perform subtle face editing simply by replacing the exemplars with another set with different facial features. A user study is conducted and shows the super-resolved images can hardly be distinguished from real images on the CelebA dataset. A qualitative comparison indicates our model outperforms methods proposed in the literature on the CelebA and WebFace dataset.

cs.CV↗

arXiv2019

Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks

Interpretation and explanation of deep models is critical towards wide adoption of systems that rely on them. In this paper, we propose a novel scheme for both interpretation as well as explanation in which, given a pretrained model, we automatically identify internal features relevant for the set of classes considered by the model, without relying on additional annotations. We interpret the model through average visualizations of this reduced set of features. Then, at test time, we explain the network prediction by accompanying the predicted class label with supporting visualizations derived from the identified features. In addition, we propose a method to address the artifacts introduced by stridded operations in deconvNet-based visualizations. Moreover, we introduce an8Flower, a dataset specifically designed for objective quantitative evaluation of methods for visual explanation.Experiments on the MNIST,ILSVRC12,Fashion144k and an8Flower datasets show that our method produces detailed explanations with good coverage of relevant features of the classes of interest

cs.CV↗

arXiv2019

Adiabatic following of terahertz surface plasmon-polaritons based on tri-layered corrugated thin film coupler

In this paper, we utilize coupled mode theory (CMT) to model the coupling of surface plasmon polaritons (SPPs) between tri-layered corrugated thin films (CTF) structure coupler in the terahertz region. Employing the stimulated raman adiabatic passage (STIRAP) quantum control technique, we propose a novel directional coupler based on SPPs evolution in tri-layered CTF in some curved configuration. Our calculated results show that the SPPs can be completely transferred from the input to the output CTF waveguides, and even we consider SPPs propagation loss, the transfer rate is still above 70%. The performance of our coupler is also robust that it is not sensitive to the geometry of device and wavelength of SPPs. As a result, our device can tolerate defect induced by fabrication and manipulate THz wave at broadband.

physics.optics↗

arXiv2018

An Analysis of Human-centered Geolocation

Online social networks contain a constantly increasing amount of images - most of them focusing on people. Due to cultural and climate factors, fashion trends and physical appearance of individuals differ from city to city. In this paper we investigate to what extent such cues can be exploited in order to infer the geographic location, i.e. the city, where a picture was taken. We conduct a user study, as well as an evaluation of automatic methods based on convolutional neural networks. Experiments on the Fashion 144k and a Pinterest-based dataset show that the automatic methods succeed at this task to a reasonable extent. As a matter of fact, our empirical results suggest that automatic methods can surpass human performance by a large margin. Further inspection of the trained models shows that human-centered characteristics, like clothing style, physical features, and accessories, are informative for the task at hand. Moreover, it reveals that also contextual features, e.g. wall type, natural environment, etc., are taken into account by the automatic methods.

cs.CV↗