An Unsupervised Deep-Learning Method for Fingerprint Classification: the CCAE Network and the Hybrid Clustering Strategy

The fingerprint classification is an important and effective method to quicken the process and improve the accuracy in the fingerprint matching process. Conventional supervised methods need a large amount of pre-labeled data and thus consume immense human resources. In this paper, we propose a new and efficient unsupervised deep learning method that can extract fingerprint features and classify fingerprint patterns automatically. In this approach, a new model named constraint convolutional auto-encoder (CCAE) is used to extract fingerprint features and a hybrid clustering strategy is applied to obtain the final clusters. A set of experiments in the NIST-DB4 dataset shows that the proposed unsupervised method exhibits the efficient performance on fingerprint classification. For example, the CCAE achieves an accuracy of 97.3% on only 1000 unlabeled fingerprints in the NIST-DB4.

Dual-Camera Super-Resolution with Aligned Attention Modules

We present a novel approach to reference-based super-resolution (RefSR) with the focus on dual-camera super-resolution (DCSR), which utilizes reference images for high-quality and high-fidelity results. Our proposed method generalizes the standard patch-based feature matching with spatial alignment operations. We further explore the dual-camera super-resolution that is one promising application of RefSR, and build a dataset that consists of 146 image pairs from the main and telephoto cameras in a smartphone. To bridge the domain gaps between real-world images and the training images, we propose a self-supervised domain adaptation strategy for real-world images. Extensive experiments on our dataset and a public benchmark demonstrate clear improvement achieved by our method over state of the art in both quantitative evaluation and visual comparisons.

Optimization and robustness of topological corner state in second-order topological photonic crystal

The second-order topological photonic crystal with 0D corner state provides a new way to investigate cavity quantum electrodynamics and develop topological nanophotonic devices with diverse functionalities. Here, we report on the optimization and robustness of topological corner state in the second-order topological photonic crystal both in theory and in experiment. The topological nanocavity is formed based on the 2D generalized Su-Schrieffer-Heeger model. The quality factor of corner state is optimized theoretically and experimentally by changing the gap between two photonic crystals or just modulating the position or size of the airholes surrounding the corner. The fabricated quality factors are further optimized by the surface passivation treatment which reduces surface absorption. A maximum quality factor of the fabricated devices is about 6000, which is the highest value ever reported for the active topological corner state. Furthermore, we demonstrate the robustness of corner state against strong disorders including the bulk defect, edge defect, and even corner defect. Our results lay a solid foundation for the further investigations and applications of the topological corner state, such as the investigation of strong coupling regime and the development of optical devices for topological nanophotonic circuitry.

Physics-constrained Deep Learning for Robust Inverse ECG Modeling

The rapid developments in advanced sensing and imaging bring about a data-rich environment, facilitating the effective modeling, monitoring, and control of complex systems. For example, the body-sensor network captures multi-channel information pertinent to the electrical activity of the heart (i.e., electrocardiograms (ECG)), which enables medical scientists to monitor and detect abnormal cardiac conditions. However, the high-dimensional sensing data are generally complexly structured and realizing the full data potential depends to a great extent on advanced analytical and predictive methods. This paper presents a physics-constrained deep learning (P-DL) framework for high-dimensional inverse ECG modeling. This method integrates the physical laws of the complex system with the advanced deep learning infrastructure for effective prediction of the system dynamics. The proposed P-DL approach is implemented to solve the inverse ECG model and predict the time-varying distribution of electric potentials in the heart from the ECG data measured by the body-surface sensor network. Experimental results show that the proposed P-DL method significantly outperforms existing methods that are commonly used in current practice.

Topological cavity based on slow light topological edge mode for broadband Purcell enhancement

Slow light in topological valley photonic crystal structures offers new possibilities to enhance light-matter interaction. We report a topological cavity based on slow light topological edge mode for broadband Purcell enhancement. The topological edge modes with large group indices over 100 can be realized with a bearded interface between two topologically distinct valley photonic crystals, featuring the greatly enhanced Purcell factor because of the increased local density of states. In the slow light regime, the topological cavity supports much more cavity modes with higher quality factor than that in the fast light regime, which is both demonstrated theoretically and experimentally. We demonstrate the cavity enables the broadband Purcell enhancement together with substantial Purcell factor, benefiting from dense cavity modes with high quality factor in a wide spectral range. It has great benefit to the realization of high-efficiency quantum-dot-based single-photon sources and entangled-photon sources with less restriction on spectral match. Such topological cavity could serve as a significant building block toward the development of photonic integrated circuits with embedded quantum emitters.

Document-level Relation Extraction as Semantic Segmentation

Document-level relation extraction aims to extract relations among multiple entity pairs from a document. Previously proposed graph-based or transformer-based models utilize the entities independently, regardless of global information among relational triples. This paper approaches the problem by predicting an entity-level relation matrix to capture local and global information, parallel to the semantic segmentation task in computer vision. Herein, we propose a Document U-shaped Network for document-level relation extraction. Specifically, we leverage an encoder module to capture the context information of entities and a U-shaped segmentation module over the image-style feature map to capture global interdependency among triples. Experimental results show that our approach can obtain state-of-the-art performance on three benchmark datasets DocRED, CDR, and GDA.

Chiral photonic circuits for deterministic spin transfer

Chiral quantum optics has attracted considerable interest in the field of quantum information science. Exploiting the spin-polarization properties of quantum emitters and engineering rational photonic nanostructures has made it possible to transform information from spin to path encoding. Here, compact chiral photonic circuits with deterministic circularly polarized chiral routing and beamsplitting are demonstrated using two laterally adjacent waveguides coupled with quantum dots. Chiral routing arises from the electromagnetic field chirality in waveguide, and beamsplitting is obtained via the evanescent field coupling. The spin- and position-dependent directional spontaneous emission are achieved by spatially selective micro-photoluminescence measurements, with a chiral contrast of up to 0.84 in the chiral photonic circuits. This makes a significant advancement for broadening the application scenarios of chiral quantum optics and developing scalable quantum photonic networks.

Hypernetwork Dismantling via Deep Reinforcement Learning

Network dismantling aims to degrade the connectivity of a network by removing an optimal set of nodes and has been widely adopted in many real-world applications such as epidemic control and rumor containment. However, conventional methods usually focus on simple network modeling with only pairwise interactions, while group-wise interactions modeled by hypernetwork are ubiquitous and critical. In this work, we formulate the hypernetwork dismantling problem as a node sequence decision problem and propose a deep reinforcement learning (DRL)-based hypernetwork dismantling framework. Besides, we design a novel inductive hypernetwork embedding method to ensure the transferability to various real-world hypernetworks. Generally, our framework builds an agent. It first generates small-scale synthetic hypernetworks and embeds the nodes and hypernetworks into a low dimensional vector space to represent the action and state space in DRL, respectively. Then trial-and-error dismantling tasks are conducted by the agent on these synthetic hypernetworks, and the dismantling strategy is continuously optimized. Finally, the well-optimized strategy is applied to real-world hypernetwork dismantling tasks. Experimental results on five real-world hypernetworks demonstrate the effectiveness of our proposed framework.

KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction

Recently, prompt-tuning has achieved promising results for certain few-shot classification tasks. The core idea of prompt-tuning is to insert text pieces (i.e., templates) into the input and transform a classification task into a masked language modeling problem. However, for relation extraction, determining an appropriate prompt template requires domain expertise, and it is cumbersome and time-consuming to obtain a suitable label word. Furthermore, there exist abundant semantic knowledge among the entities and relations that cannot be ignored. To this end, we focus on incorporating knowledge into prompt-tuning for relation extraction and propose a knowledge-aware prompt-tuning approach with synergistic optimization (KnowPrompt). Specifically, we inject entity and relation knowledge into prompt construction with learnable virtual template words as well as answer words and synergistically optimize their representation with knowledge constraints. Extensive experimental results on five datasets with standard and low-resource settings demonstrate the effectiveness of our approach.

Enhanced emission from a single quantum dot in a microdisk at a deterministic diabolical point

We report on controllable cavity modes through controlling the backscattering by two identical scatterers. Periodic changes of the backscattering coupling between two degenerate cavity modes are observed with the angle between two scatterers and elucidated by a theoretical model using two-mode approximation and numerical simulations. The periodically appearing single-peak cavity modes indicate mode degeneracy at diabolical points. Then interactions between single quantum dots and cavity modes are investigated. Enhanced emission of a quantum dot with a six-fold intensity increase is obtained in a microdisk at a diabolical point. This method to control cavity modes allows large-scale integration, high reproducibility and fexible design of the size, location, quantity and shape for scatterers, which can be applied for integrated photonic structures with scatterer-modified light-matter interaction.