Speaker embedding is an important front-end module to explore discriminative speaker features for many speech applications where speaker information is needed. Current SOTA backbone networks for speaker embedding are designed to aggregate multi-scale features from an utterance with multi-branch network architectures for speaker representation. However, naively adding many branches of multi-scale features with the simple fully convolutional operation could not efficiently improve the performance due to the rapid increase of model parameters and computational complexity. Therefore, in the most current state-of-the-art network architectures, only a few branches corresponding to a limited number of temporal scales could be designed for speaker embeddings. To address this problem, in this paper, we propose an effective temporal multi-scale (TMS) model where multi-scale branches could be efficiently designed in a speaker embedding network almost without increasing computational costs. The new model is based on the conventional TDNN, where the network architecture is smartly separated into two modeling operators: a channel-modeling operator and a temporal multi-branch modeling operator. Adding temporal multi-scale in the temporal multi-branch operator needs only a little bit increase of the number of parameters, and thus save more computational budget for adding more branches with large temporal scales. Moreover, in the inference stage, we further developed a systemic re-parameterization method to convert the TMS-based model into a single-path-based topology in order to increase inference speed. We investigated the performance of the new TMS method for automatic speaker verification (ASV) on in-domain and out-of-domain conditions. Results show that the TMS-based model obtained a significant increase in the performance over the SOTA ASV models, meanwhile, had a faster inference speed.
Facial expressions are a form of non-verbal communication that humans perform seamlessly for meaningful transfer of information. Most of the literature addresses the facial expression recognition aspect however, with the advent of Generative Models, it has become possible to explore the affect space in addition to mere classification of a set of expressions. In this article, we propose a generative model architecture which robustly generates a set of facial expressions for multiple character identities and explores the possibilities of generating complex expressions by combining the simple ones.
Recently, there has been growing research on developing interference-aware routing (IAR) protocols for supporting multiple concurrent transmission in next-generation wireless communication systems. The existing IAR protocols do not consider node cooperation while establishing the routes because motivating the nodes to cooperate and modeling that cooperation is not a trivial task. In addition, the information about the cooperative behavior of a node is not directly visible to neighboring nodes. Therefore, in this paper, we develop a new routing method in which the nodes' cooperation information is utilized to improve the performance of edge computing-enabled 5G networks. The proposed metric is a function of created and received interference in the network. The received interference term ensures that the Signal to Interference plus Noise Ratio (SINR) at the route remains above the threshold value, while the created interference term ensures that those nodes are selected to forward the packet that creates low interference for other nodes. The results show that the proposed solution improves ad hoc networks' performance compared to conventional routing protocols in terms of high network throughput and low outage probability.
Since proposed in the 70s, the Non-Equilibrium Green Function (NEGF) method has been recognized as a standard approach to quantum transport simulations. Although it achieves superiority in simulation accuracy, the tremendous computational cost makes it unbearable for high-throughput simulation tasks such as sensitivity analysis, inverse design, etc. In this work, we propose AD-NEGF, to our best knowledge the first end-to-end differentiable NEGF model for quantum transport simulations. We implement the entire numerical process in PyTorch, and design customized backward pass with implicit layer techniques, which provides gradient information at an affordable cost while guaranteeing the correctness of the forward simulation. The proposed model is validated with applications in calculating differential physical quantities, empirical parameter fitting, and doping optimization, which demonstrates its capacity to accelerate the material design process by conducting gradient-based parameter optimization.
Multi-spectral quantitative phase imaging (MS-QPI) is a cutting-edge label-free technique to determine the morphological changes, refractive index variations and spectroscopic information of the specimens. The bottleneck to implement this technique to extract quantitative information, is the need of more than two measurements for generating MS-QPI images. We propose a single-shot MS-QPI technique using highly spatially sensitive digital holographic microscope assisted with deep neural network (DNN). Our method first acquires the interferometric datasets corresponding to multiple wavelengths ({\lambda}=532, 633 and 808 nm used here). The acquired datasets are used to train generative adversarial network (GAN) to generate multi-spectral quantitative phase maps from a single input interferogram. The network is trained and validated on two different samples, the optical waveguide and a MG63 osteosarcoma cells. Further, validation of the framework is performed by comparing the predicted phase maps with experimentally acquired and processed multi-spectral phase maps. The current MS-QPI+DNN framework can further empower spectroscopic QPI to improve the chemical specificity without complex instrumentation and color-cross talk.
We present an information-theoretic regularization technique for few-shot novel view synthesis based on neural implicit representation. The proposed approach minimizes potential reconstruction inconsistency that happens due to insufficient viewpoints by imposing the entropy constraint of the density in each ray. In addition, to alleviate the potential degenerate issue when all training images are acquired from almost redundant viewpoints, we further incorporate the spatially smoothness constraint into the estimated images by restricting information gains from a pair of rays with slightly different viewpoints. The main idea of our algorithm is to make reconstructed scenes compact along individual rays and consistent across rays in the neighborhood. The proposed regularizers can be plugged into most of existing neural volume rendering techniques based on NeRF in a straightforward way. Despite its simplicity, we achieve consistently improved performance compared to existing neural view synthesis methods by large margins on multiple standard benchmarks. Our project website is available at \url{http://cvlab.snu.ac.kr/research/InfoNeRF}.
The completeness (in terms of content) of financial documents is a fundamental requirement for investment funds. To ensure completeness, financial regulators spend a huge amount of time for carefully checking every financial document based on the relevant content requirements, which prescribe the information types to be included in financial documents (e.g., the description of shares' issue conditions). Although several techniques have been proposed to automatically detect certain types of information in documents in various application domains, they provide limited support to help regulators automatically identify the text chunks related to financial information types, due to the complexity of financial documents and the diversity of the sentences characterizing an information type. In this paper, we propose FITI, an artificial intelligence (AI)-based method for tracing content requirements in financial documents. Given a new financial document, FITI selects a set of candidate sentences for efficient information type identification. Then, FITI uses a combination of rule-based and data-centric approaches, by leveraging information retrieval (IR) and machine learning (ML) techniques that analyze the words, sentences, and contexts related to an information type, to rank candidate sentences. Finally, using a list of indicator phrases related to each information type, a heuristic-based selector, which considers both the sentence ranking and the domain-specific phrases, determines a list of sentences corresponding to each information type. We evaluated FITI by assessing its effectiveness in tracing financial content requirements in 100 financial documents. Experimental results show that FITI provides accurate identification with average precision and recall values of 0.824 and 0.646, respectively. Furthermore, FITI can detect about 80% of missing information types in financial documents.
Neural networks are suggested for learning a map from $d$-dimensional samples with any underlying dependence structure to multivariate uniformity in $d'$ dimensions. This map, termed DecoupleNet, is used for dependence model assessment and selection. If the data-generating dependence model was known, and if it was among the few analytically tractable ones, one such transformation for $d'=d$ is Rosenblatt's transform. DecoupleNets only require an available sample and are applicable to $d'<d$, in particular $d'=2$. This allows for simpler model assessment and selection without loss of information, both numerically and, because $d'=2$, graphically. Through simulation studies based on data from various copulas, the feasibility and validity of this novel approach is demonstrated. Applications to real world data illustrate its usefulness for model assessment and selection.
Moving objects are present in most scenes of our life. However they can be very problematic for classical SLAM algorithms that assume the scene to be rigid. This assumption limits the applicability of those algorithms as they are unable to accurately estimate the camera pose and world structure in many scenarios. Some SLAM systems have been proposed to detect and mask out dynamic objects, making the static scene assumption valid. However this information can allow the system to track objects within the scene, while tracking the camera, which can be crucial for some applications. In this paper we present TwistSLAM a semantic, dynamic, stereo SLAM system that can track dynamic objects in the scene. Our algorithm creates clusters of points according to their semantic class. It uses the static parts of the environment to robustly localize the camera and tracks the remaining objects. We propose a new formulation for the tracking and the bundle adjustment to take in account the characteristics of mechanical joints between clusters to constrain and improve their pose estimation. We evaluate our approach on several sequences from a public dataset and show that we improve camera and object tracking compared to state of the art.
Incorporating data-specific domain knowledge in deep networks explicitly can provide important cues beneficial for lesion detection and can mitigate the need for diverse heterogeneous datasets for learning robust detectors. In this paper, we exploit the domain information present in computed tomography (CT) scans and propose a robust universal lesion detection (ULD) network that can detect lesions across all organs of the body by training on a single dataset, DeepLesion. We analyze CT-slices of varying intensities, generated using heuristically determined Hounsfield Unit(HU) windows that individually highlight different organs and are given as inputs to the deep network. The features obtained from the multiple intensity images are fused using a novel convolution augmented multi-head self-attention module and subsequently, passed to a Region Proposal Network (RPN) for lesion detection. In addition, we observed that traditional anchor boxes used in RPN for natural images are not suitable for lesion sizes often found in medical images. Therefore, we propose to use lesion-specific anchor sizes and ratios in the RPN for improving the detection performance. We use self-supervision to initialize weights of our network on the DeepLesion dataset to further imbibe domain knowledge. Our proposed Domain Knowledge augmented Multi-head Attention based Universal Lesion Detection Network DMKA-ULD produces refined and precise bounding boxes around lesions across different organs. We evaluate the efficacy of our network on the publicly available DeepLesion dataset which comprises of approximately 32K CT scans with annotated lesions across all organs of the body. Results demonstrate that we outperform existing state-of-the-art methods achieving an overall sensitivity of 87.16%.