Search Results for author:
Found 478 papers, 164 papers with code
Deep Mixture of Experts via Shallow Embedding
Larger networks generally have greater representational power at the cost of increased computational complexity.
Fast Weight Long Short-Term Memory
Associative memory using fast weights is a short-term memory mechanism that substantially improves the memory capacity and time scale of recurrent neural networks (RNNs).
A comparison of recent waveform generation and acoustic modeling methods for neural-network-based speech synthesis
Recent advances in speech synthesis suggest that limitations such as the lossy nature of the amplitude spectrum with minimum phase approximation and the over-smoothing effect in acoustic modeling can be overcome by using advanced machine learning approaches.
Video Captioning via Hierarchical Reinforcement Learning
Video captioning is the task of automatically generating a textual description of the actions in a video.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
Can we steal your vocal identity from the Internet?: Initial investigation of cloning Obama's voice using GAN, WaveNet and low-quality found data
Thanks to the growing availability of spoofing databases and rapid advances in using them, systems for detecting voice spoofing attacks are becoming more and more capable, and error rates close to zero are being reached for the ASVspoof2015 database.
Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks
Here we present the Flexpoint data format, aiming at a complete replacement of 32-bit floating point format training and inference, designed to support modern deep network topologies without modifications.
IDK Cascades: Fast Deep Learning by Learning not to Overthink
Advances in deep learning have led to substantial increases in prediction accuracy but have been accompanied by increases in the cost of rendering predictions.
Deep Reinforcement Learning for Visual Object Tracking in Videos
In this paper we introduce a fully end-to-end approach for visual tracking in videos that learns to predict the bounding box locations of a target object at every frame.
Clipper: A Low-Latency Online Prediction Serving System
In this paper, we introduce Clipper, a general-purpose low-latency prediction serving system.
Stochastic Averaging for Constrained Optimization with Application to Online Resource Allocation
Existing approaches to resource allocation for nowadays stochastic networks are challenged to meet fast convergence and tolerable delay requirements.
Classification of Neurological Gait Disorders Using Multi-task Feature Learning
An advanced machine learning method, multi-task feature learning (MTFL), is used to jointly train classification models of a subject's gait in three classes, post-stroke, PD and healthy gait.
Robust Learning with Kernel Mean p-Power Error Loss
Correntropy is a second order statistical measure in kernel space, which has been successfully applied in robust learning and signal processing.
On Multiplicative Multitask Feature Learning
We prove that this framework is mathematically equivalent to the widely used multitask feature learning methods that are based on a joint regularization of all model parameters, but with a more general form of regularizers.
A multi-task learning model for malware classification with useful file access pattern from API call sequence
Based on API call sequences, semantic-aware and machine learning (ML) based malware classifiers can be built for malware detection or classification.
Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis
Generating versatile and appropriate synthetic speech requires control over the output expression separate from the spoken text.
PSDF Fusion: Probabilistic Signed Distance Function for On-the-fly 3D Data Fusion and Scene Reconstruction
We propose a novel 3D spatial representation for data fusion and scene reconstruction.
Investigating accuracy of pitch-accent annotations in neural network-based speech synthesis and denoising effects
We investigated the impact of noisy linguistic features on the performance of a Japanese speech synthesis system based on neural network that uses WaveNet vocoder.
Non-asymptotic entanglement distillation
For isotropic states, it can be further simplified to a linear program.
Quantum Physics
Neural source-filter-based waveform model for statistical parametric speech synthesis
Neural waveform models such as the WaveNet are used in many recent text-to-speech systems, but the original WaveNet is quite slow in waveform generation because of its autoregressive (AR) structure.
Audiovisual speaker conversion: jointly and simultaneously transforming facial expression and acoustic characteristics
Transforming the facial and acoustic features together makes it possible for the converted voice and facial expressions to be highly correlated and for the generated target speaker to appear and sound natural.
Learning to Compose Topic-Aware Mixture of Experts for Zero-Shot Video Captioning
Although promising results have been achieved in video captioning, existing models are limited to the fixed inventory of activities in the training corpus, and do not generalize to open vocabulary scenarios.
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
Vision-language navigation (VLN) is the task of navigating an embodied agent to carry out natural language instructions inside real 3D environments.
Ranked #2 on
Vision-Language Navigation
on Room2Room
Guided Feature Selection for Deep Visual Odometry
We present a novel end-to-end visual odometry architecture with guided feature selection based on deep convolutional recurrent neural networks.
MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment
In this paper, we present Moment Alignment Network (MAN), a novel framework that unifies the candidate moment encoding and temporal structural reasoning in a single-shot feed-forward network.
Conditional Graph Neural Processes: A Functional Autoencoder Approach
Thus, we refer to our model as Conditional Graph Neural Process (CGNP).
Explanatory Graphs for CNNs
This paper introduces a graphical model, namely an explanatory graph, which reveals the knowledge hierarchy hidden inside conv-layers of a pre-trained CNN.
Group Linguistic Bias Aware Neural Response Generation
For practical chatbots, one of the essential factor for improving user experience is the capability of customizing the talking style of the agents, that is, to make chatbots provide responses meeting users{'} preference on language styles, topics, etc.
Predicting Users' Negative Feedbacks in Multi-Turn Human-Computer Dialogues
Besides, strategies of obtaining distance supervision data for pre-training are also discussed in this work.
On Algorithms for Sparse Multi-factor NMF
Nonnegative matrix factorization (NMF) is a popular data analysis method, the objective of which is to decompose a matrix with all nonnegative components into the product of two other nonnegative matrices.
Interpretable CNNs for Object Classification
This paper proposes a generic method to learn interpretable convolutional filters in a deep convolutional neural network (CNN) for object classification, where each interpretable filter encodes features of a specific object part.
Residual Attention based Network for Hand Bone Age Assessment
The hierarchical attention components of the residual attention subnet force our network to focus on the key components of the X-ray images and generate the final predictions as well as the associated visual supports, which is similar to the assessment procedure of clinicians.
Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization
We evaluate the performance of dynamic reallocation methods in training deep convolutional networks and show that our method outperforms previous static and dynamic reparameterization methods, yielding the best accuracy for a fixed parameter budget, on par with accuracies obtained by iteratively pruning a pre-trained dense model.
Attention-driven Tree-structured Convolutional LSTM for High Dimensional Data Understanding
In order to address these limitations, we present tree-structured ConvLSTM models for tree-structured image analysis tasks which can be trained end-to-end.
Visual Query Answering by Entity-Attribute Graph Matching and Reasoning
Based on GEA and Q, we provide techniques to find matches of Q in GEA, as the answer of Qnl in Img.
DeepCenterline: a Multi-task Fully Convolutional Network for Centerline Extraction
The proposed method generates well-positioned centerlines, exhibiting lower number of missing branches and is more robust in the presence of minor imperfections of the object segmentation mask.
Joint training framework for text-to-speech and voice conversion using multi-source Tacotron and WaveNet
We propose using an extended model architecture of Tacotron, that is a multi-source sequence-to-sequence model with a dual attention mechanism as the shared model for both the TTS and VC tasks.
Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora
When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers and train a multi-speaker TTS model instead.
Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry
Most previous learning-based visual odometry (VO) methods take VO as a pure tracking problem.
Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation
The overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs.
ACE: Adapting to Changing Environments for Semantic Segmentation
However, neural classifiers are often extremely brittle when confronted with domain shift---changes in the input distribution that occur over time.
Maximum Correntropy Criterion with Variable Center
The kernel function in correntropy is usually restricted to the Gaussian function with center located at zero.
Logician: A Unified End-to-End Neural Approach for Open-Domain Information Extraction
In this paper, we consider the problem of open information extraction (OIE) for extracting entity and relation level intermediate structures from sentences in open-domain.
Neural source-filter waveform models for statistical parametric speech synthesis
Other models such as Parallel WaveNet and ClariNet bring together the benefits of AR and IAF-based models and train an IAF model by transferring the knowledge from a pre-trained AR teacher to an IAF student without any sequential transformation.
Multi-Kernel Correntropy for Robust Learning
In a recent work, the concept of mixture correntropy (MC) was proposed to improve the learning performance, where the kernel function is a mixture Gaussian kernel, namely a linear combination of several zero-mean Gaussian kernels with different widths.
Speaker Anonymization Using X-vector and Neural Waveform Models
One solution to mitigate these concerns involves the concealing of speaker identities before the sharing of speech data.
One-shot entanglement distillation beyond LOCC
We show in particular that the $\varepsilon$-error one-shot distillable entanglement of any pure state is the same under all sets of operations ranging from one-way LOCC to separability-preserving operations or operations preserving the set of states with positive partial transpose, and can be computed exactly as a quadratically constrained linear program.
Quantum Physics Mathematical Physics Mathematical Physics
Recognizing License Plates in Real-Time
To enable real-time and accurate license plate recognition, in this work, we propose a set of techniques: 1) a contour reconstruction method along with edge-detection to quickly detect the candidate plates; 2) a simple zero-one-alternation scheme to effectively remove the fake top and bottom borders around plates to facilitate more accurate segmentation of characters on plates; 3) a set of techniques to augment the training data, incorporate SIFT features into the CNN network, and exploit transfer learning to obtain the initial parameters for more effective training; and 4) a two-phase verification procedure to determine the correct plate at low cost, a statistical filtering in the plate detection stage to quickly remove unwanted candidates, and the accurate CR results after the CR process to perform further plate verification without additional processing.
Self-Supervised Dialogue Learning
The sequential order of utterances is often meaningful in coherent dialogues, and the order changes of utterances could lead to low-quality and incoherent conversations.
Modeling the Uncertainty in Electronic Health Records: a Bayesian Deep Learning Approach
Deep learning models have exhibited superior performance in predictive tasks with the explosively increasing Electronic Health Records (EHR).
Privacy-preserving Distributed Machine Learning via Local Randomization and ADMM Perturbation
With the proliferation of training data, distributed machine learning (DML) is becoming more competent for large-scale learning tasks.
Local Supports Global: Deep Camera Relocalization with Sequence Enhancement
We propose to leverage the local information in image sequences to support global camera relocalization.
Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry
As single-view depth estimation is an ill-posed problem, and photometric loss is incapable of discriminating distortion artifacts of warped images, the estimated depth is vague and pose is inaccurate.
Latent Part-of-Speech Sequences for Neural Machine Translation
In this work, we introduce a new latent variable model, LaSyn, that captures the co-dependence between syntax and semantics, while allowing for effective and efficient inference over the latent space.
Initial investigation of an encoder-decoder end-to-end TTS framework using marginalization of monotonic hard latent alignments
The advantages of our approach are that we can simplify many modules for the soft attention and that we can train the end-to-end TTS model using a single likelihood function.
Detecting Deep Neural Network Defects with Data Flow Analysis
Deep neural networks (DNNs) are shown to be promising solutions in many challenging artificial intelligence tasks.
Data Sanity Check for Deep Learning Systems via Learnt Assertions
But the statistical nature of DL makes it quite vulnerable to invalid inputs, i. e., those cases that are not considered in the training phase of a DL model.
Multi-modal Deep Analysis for Multimedia
To address the two scientific problems, we investigate them from the following aspects: 1) multi-modal correlational representation: multi-modal fusion of data across different modalities, and 2) multi-modal data and knowledge fusion: multi-modal fusion of data with domain knowledge.
Effect of choice of probability distribution, randomness, and search methods for alignment modeling in sequence-to-sequence text-to-speech synthesis using hard alignment
Sequence-to-sequence text-to-speech (TTS) is dominated by soft-attention-based methods.
Transferring neural speech waveform synthesizers to musical instrument sounds generation
Recent neural waveform synthesizers such as WaveNet, WaveGlow, and the neural-source-filter (NSF) model have shown good performance in speech synthesis despite their different methods of waveform generation.
Latent Suicide Risk Detection on Microblog via Suicide-Oriented Word Embeddings and Layered Attention
Despite detection of suicidal ideation on social media has made great progress in recent years, people's implicitly and anti-real contrarily expressed posts still remain as an obstacle, constraining the detectors to acquire higher satisfactory performance.
Cross-Channel Intragroup Sparsity Neural Network
Modern deep neural networks rely on overparameterization to achieve state-of-the-art generalization.
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech
Spoofing attacks within a logical access (LA) scenario are generated with the latest speech synthesis and voice conversion technologies, including state-of-the-art neural acoustic and waveform model techniques.
Disparity-preserved Deep Cross-platform Association for Cross-platform Video Recommendation
However, there remain two unsolved challenges: i) there exist inconsistencies in cross-platform association due to platform-specific disparity, and ii) data from distinct platforms may have different semantic granularities.
Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation
Visual navigation is a task of training an embodied agent by intelligently navigating to a target object (e. g., television) using only visual observations.
Adaptive Activation Network and Functional Regularization for Efficient and Flexible Deep Multi-Task Learning
In this paper, we propose a novel deep learning model called Task Adaptive Activation Network (TAAN) that can automatically learn the optimal network architecture for MTL.
Domain-Aware Dynamic Networks
In this work, we propose a method to improve the model capacity without increasing inference-time complexity.
"How do urban incidents affect traffic speed?" A Deep Graph Convolutional Network for Incident-driven Traffic Speed Prediction
Combining above methods, we propose a Deep Incident-Aware Graph Convolutional Network (DIGC-Net) to effectively incorporate urban traffic incident, spatio-temporal, periodic and context features for traffic speed prediction.
Theme-Matters: Fashion Compatibility Learning via Theme Attention
This model associates themes with the pairwise compatibility with attention, and thus compute the outfit-wise compatibility.
Fully Convolutional Graph Neural Networks using Bipartite Graph Convolutions
Graph neural networks have been adopted in numerous applications ranging from learning relational representations to modeling data on irregular domains such as point clouds, social graphs, and molecular structures.
Deep Learning for Learning Graph Representations
Mining graph data has become a popular research topic in computer science and has been widely studied in both academia and industry given the increasing amount of network data in the recent years.
Reject Illegal Inputs with Generative Classifier Derived from Any Discriminative Classifier
Experiments on illegal inputs, including adversarial examples, samples with common corruptions, and out-of-distribution~(OOD) samples show that allowed to reject a portion of test samples, SDIM-\emph{logit} significantly improves the performance on the left test sets.
Automated Pavement Crack Segmentation Using U-Net-based Convolutional Neural Network
In this paper, we propose a deep learning technique based on a convolutional neural network to perform segmentation tasks on pavement crack images.
Domain Embedded Multi-model Generative Adversarial Networks for Image-based Face Inpainting
We firstly represent only face regions using the latent variable as the domain knowledge and combine it with the non-face parts textures to generate high-quality face images with plausible contents.
2.75D: Boosting learning by representing 3D Medical imaging to 2D features for small data
Such performance gain is more pronounced with transfer learning or in the case of limited training data.
Improving Sampling Accuracy of Stochastic Gradient MCMC Methods via Non-uniform Subsampling of Gradients
In our practical implementation of EWSG, the non-uniform subsampling is performed efficiently via a Metropolis-Hastings chain on the data index, which is coupled to the MCMC algorithm.
Category-wise Attack: Transferable Adversarial Examples for Anchor Free Object Detection
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbations can completely change the classification results.
Bridge the Domain Gap Between Ultra-wide-field and Traditional Fundus Images via Adversarial Domain Adaptation
We design a regularisation technique to regulate the domain adaptation.
Synergic Adversarial Label Learning for Grading Retinal Diseases via Knowledge Distillation and Multi-task Learning
In addition, we conduct additional experiments to show the effectiveness of SALL from the aspects of reliability and interpretability in the context of medical imaging application.
An adaptive neuro-fuzzy model for attitude estimation and 2 control a 3 DOF system
To evaluate the performance of the AN-FIS controller in closed-loop simulation, an ANFIS observer is used to estimate the attitude and angular velocities of the satellite using magnetometer, sun sensor and data gyro data.
How fine can fine-tuning be? Learning efficient language models
Given a language model pre-trained on massive unlabeled text corpora, only very light supervised fine-tuning is needed to learn a task: the number of fine-tuning steps is typically five orders of magnitude lower than the total parameter count.
Self-Supervised Deep Visual Odometry with Online Adaptation
In this paper, we propose an online meta-learning algorithm to enable VO networks to continuously adapt to new environments in a self-supervised manner.
Design Choices for X-vector Based Speaker Anonymization
The recently proposed x-vector based anonymization scheme converts any input voice into that of a random pseudo-speaker.
Investigation of learning abilities on linguistic features in sequence-to-sequence text-to-speech synthesis
Our experiments suggest that a) a neural sequence-to-sequence TTS system should have a sufficient number of model parameters to produce high quality speech, b) it should also use a powerful encoder when it takes characters as inputs, and c) the encoder still has a room for improvement and needs to have an improved architecture to learn supra-segmental features more appropriately.
More Practical and Adaptive Algorithms for Online Quantum State Learning
This regret bound depends only on the maximum rank $M$ of measurements rather than the number of qubits, which takes advantage of low-rank measurements.
A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
Neural Architecture Search (NAS) is just such a revolutionary algorithm, and the related research work is complicated and rich.
Eigen-GNN: A Graph Structure Preserving Plug-in for GNNs
Graph Neural Networks (GNNs) are emerging machine learning models on graphs.
Learning Continuous-Time Dynamics by Stochastic Differential Networks
Learning continuous-time stochastic dynamics is a fundamental and essential problem in modeling sporadic time series, whose observations are irregular and sparse in both time and dimension.
The curious case of developmental BERTology: On sparsity, transfer learning, generalization and the brain
In this essay, we explore a point of intersection between deep learning and neuroscience, through the lens of large language models, transfer learning and network compression.
Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification: Fundamentals
Recent years have seen growing efforts to develop spoofing countermeasures (CMs) to protect automatic speaker verification (ASV) systems from being deceived by manipulated or artificial inputs.
A SLAM Map Restoration Algorithm Based on Submaps and an Undirected Connected Graph
To solve the missing map problem, which is an issue in many applications , after the tracking is lost, based on monocular visual SLAM, we present a method of reconstructing a complete global map of UAV datasets by sequentially merging the submaps via the corresponding undirected connected graph.
Learning Tuple Compatibility for Conditional OutfitRecommendation
Our contributions include: 1) Designing a Mixed Category Attention Net (MCAN) which integrates both fine-grained and coarse category information into recommendation and learns the compatibility among fashion tuples.
Cultural Vocal Bursts Intensity Prediction
Recommendation Systems
Crossing-Domain Generative Adversarial Networks for Unsupervised Multi-Domain Image-to-Image Translation
In this work, we propose a general framework for unsupervised image-to-image translation across multiple domains, which can translate images from domain X to any a domain without requiring direct training between the two domains involved in image translation.
Elliptic Blowup Equations for 6d SCFTs. IV: Matters
Given the recent geometrical classification of 6d $(1, 0)$ SCFTs, a major question is how to compute for this large class their elliptic genera.
High Energy Physics - Theory Mathematical Physics Mathematical Physics
Intragroup sparsity for efficient inference
This work studies intragroup sparsity, a fine-grained structural constraint on network weight parameters.
Towards A Unified Understanding and Improving of Adversarial Transferability
We discover and prove the negative correlation between the adversarial transferability and the interaction inside adversarial perturbations.
Holistic Combination of Structural and Textual Code Information for Context based API Recommendation
APIRec-CST is a deep learning model that combines the API usage with the text information in the source code based on an API Context Graph Network and a Code Token Network that simultaneously learn structural and textual features for API recommendation.
End-to-End Text-to-Speech using Latent Duration based on VQ-VAE
Explicit duration modeling is a key to achieving robust and efficient alignment in text-to-speech synthesis (TTS).
SWIPENET: Object detection in noisy underwater images
Moreover, inspired by the human education process that drives the learning from easy to hard concepts, we here propose the CMA training paradigm that first trains a clean detector which is free from the influence of noisy data.
Fast Local Attack: Generating Local Adversarial Examples for Object Detectors
The deep neural network is vulnerable to adversarial examples.
A Survey on Curriculum Learning
We discuss works on curriculum learning within a general CL framework, elaborating on how to design a manually predefined curriculum or an automatic curriculum.
Pretraining Strategies, Waveform Model Choice, and Acoustic Configurations for Multi-Speaker End-to-End Speech Synthesis
We explore pretraining strategies including choice of base corpus with the aim of choosing the best strategy for zero-shot multi-speaker end-to-end synthesis.
A Predicate-Function-Argument Annotation of Natural Language for Open-Domain Information eXpression
Based on the same platform of OIX, the OIE strategies are reusable, and people can select a set of strategies to assemble their algorithm for a specific task so that the adaptability may be significantly increased.
Shortcuts to Adiabaticity for the Quantum Rabi Model: Efficient Generation of Giant Entangled Cat States via Parametric Amplification
We propose a method for the fast generation of nonclassical ground states of the Rabi model in the ultrastrong and deep-strong coupling regimes via the shortcuts-to-adiabatic (STA) dynamics.
Quantum Physics
Leveraging Regular Fundus Images for Training UWF Fundus Diagnosis Models via Adversarial Learning and Pseudo-Labeling
We propose the use of a modified cycle generative adversarial network (CycleGAN) model to bridge the gap between regular and UWF fundus and generate additional UWF fundus images for training.
Cooling-Aware Resource Allocation and Load Management for Mobile Edge Computing Systems
Driven by explosive computation demands of Internet of Things (IoT), mobile edge computing (MEC) provides a promising technique to enhance the computation capability for mobile users.
Partially Connected Automated Vehicle Cooperative Control Strategy with a Deep Reinforcement Learning Approach
This paper proposes a cooperative strategy of connected and automated vehicles (CAVs) longitudinal control for partially connected and automated traffic environment based on deep reinforcement learning (DRL) algorithm, which enhances the string stability of mixed traffic, car following efficiency, and energy efficiency.
Spatial Heterogeneity Automatic Detection and Estimation
Spatial regression is widely used for modeling the relationship between a dependent variable and explanatory covariates.
Methodology
Joint Optimization of Trajectory, Propulsion and Thrust Powers for Covert UAV-on-UAV Video Tracking and Surveillance
Autonomous tracking of suspicious unmanned aerial vehicles (UAVs) by legitimate monitoring UAVs (or monitors) can be crucial to public safety and security.
Generalizable control for multiparameter quantum metrology
Here we study the generalizability of optimal control, namely, optimal controls that can be systematically updated across a range of parameters with minimal cost.
Quantum Physics
The dynamic energy balance in earthquakes expressed by fault surface morphology
The fault surface morphology is the direct result of the microscopic processes near the crack tip or on the frictional interface.
Geophysics
A Marching Cube Algorithm Based on Edge Growth
When only the main contour of the 3D model needs to be organized, the algorithm performs well.
3D Reconstruction
Graphics
A Closer Look at Temporal Sentence Grounding in Videos: Dataset and Metric
All the results demonstrate that the re-organized dataset splits and new metric can better monitor the progress in TSGV.
Explicit Perturbations to the Stabilizer $τ= {\rm i}$ of Modular $A^\prime_5$ Symmetry and Leptonic CP Violation
In a class of neutrino mass models with modular flavor symmetries, it has been observed that CP symmetry is preserved at the fixed point (or stabilizer) of the modulus parameter $\tau = {\rm i}$, whereas significant CP violation emerges within the neighbourhood of this stabilizer.
High Energy Physics - Phenomenology
ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speech
The ASVspoof initiative was conceived to spearhead research in anti-spoofing for automatic speaker verification (ASV).
Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
In this paper, we systematically discuss and define the two common types of label noise in medical images - disagreement label noise from inconsistency expert opinions and single-target label noise from wrong diagnosis record.
A Hybrid Quantum-Classical Hamiltonian Learning Algorithm
Hamiltonian learning is crucial to the certification of quantum devices and quantum simulators.
One Network Fits All? Modular versus Monolithic Task Formulations in Neural Networks
Can deep learning solve multiple tasks simultaneously, even when they are unrelated and very different?
A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection
A great deal of recent research effort on speech spoofing countermeasures has been invested into back-end neural networks and training criteria.
Online Learning of a Probabilistic and Adaptive Scene Representation
Constructing and maintaining a consistent scene model on-the-fly is the core task for online spatial perception, interpretation, and action.
An Initial Investigation for Detecting Partially Spoofed Audio
By definition, partially-spoofed utterances contain a mix of both spoofed and bona fide segments, which will likely degrade the performance of countermeasures trained with entirely spoofed utterances.
Joint User Identification, Channel Estimation, and Signal Detection for Grant-Free NOMA
To address the problem that the exact calculation of the messages exchanged within CSCE and between the two modules is complicated due to phase ambiguity issues, this paper proposes a rotationally invariant Gaussian mixture (RIGM) model, and develops an efficient JUICESD-RIGM algorithm.
Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition
For example, there are estimated more than 40 different kinds of retinal diseases with variable morbidity, however with more than 30+ conditions are very rare from the global patient cohorts, which results in a typical long-tailed learning problem for deep learning-based screening models.
Infrastructure Assisted Constrained Connected Automated Vehicle Trajectory Optimization on Curved Roads: A Spatial Formulation on a Curvilinear Coordinate
This paper presents an infrastructure assisted constrained connected automated vehicles (CAVs) trajectory optimization method on curved roads.
Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge
We investigate the theoretical connections between graph signal processing and graph embedding models and formulate the graph embedding model as a general graph signal process with a corresponding graph filter.
Imperceptible Adversarial Examples for Fake Image Detection
Fooling people with highly realistic fake images generated with Deepfake or GANs brings a great social disturbance to our society.
Transferable Adversarial Examples for Anchor Free Object Detection
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbation can completely change prediction result.
Visual Question Rewriting for Increasing Response Rate
Offline experiments and mechanical Turk based evaluations show that it is possible to rewrite bland questions in a more detailed and attractive way to increase the response rate, and images can be helpful.
Mobile Optical Communications Using Second Harmonic of Intra-Cavity Laser
In this paper, we propose an intra-cavity SHG RBCom system to simplify the system design and improve the energy conversion efficiency.
Over-the-Air Federated Multi-Task Learning
In this letter, we introduce over-the-air computation into the communication design of federated multi-task learning (FMTL), and propose an over-the-air federated multi-task learning (OA-FMTL) framework, where multiple learning tasks deployed on edge devices share a non-orthogonal fading channel under the coordination of an edge server (ES).
ReFormer: The Relational Transformer for Image Captioning
To improve the quality of image captioning, we propose a novel architecture ReFormer -- a RElational transFORMER to generate features with relation information embedded and to explicitly express the pair-wise relationships between objects in the image.
Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization
In this work, we explore unsupervised domain adaptation in retinal vessel segmentation by using entropy-based adversarial learning and transfer normalization layer to train a segmentation network, which generalizes well across domains and requires no annotation of the target domain.
A Hypothesis for the Aesthetic Appreciation in Neural Networks
This paper proposes a hypothesis for the aesthetic appreciation that aesthetic images make a neural network strengthen salient concepts and discard inessential concepts.
SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation
Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based models for code intelligence.
Interpreting Attributions and Interactions of Adversarial Attacks
This paper aims to explain adversarial attacks in terms of how adversarial perturbations contribute to the attacking task.
Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces
Generative adversary network (GAN) generated high-realistic human faces have been used as profile images for fake social media accounts and are visually challenging to discern from real ones.
ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection
In addition to a continued focus upon logical and physical access tasks in which there are a number of advances compared to previous editions, ASVspoof 2021 introduces a new task involving deepfake speech detection.
Tolerating Adversarial Attacks and Byzantine Faults in Distributed Machine Learning
In addition, Byzantine faults including software, hardware, network issues occur in distributed systems which also lead to a negative impact on the prediction outcome.
Robust Attentive Deep Neural Network for Exposing GAN-generated Faces
However, images from existing public datasets do not represent real-world scenarios well enough in terms of view variations and data distributions (where real faces largely outnumber synthetic faces).
Sentence Matching with Syntax- and Semantics-Aware BERT
Sentence matching aims to identify the special relationship between two sentences, and plays a key role in many natural language processing tasks.
A Survey on Temporal Sentence Grounding in Videos
In this survey, we give a comprehensive overview for TSGV, which i) summarizes the taxonomy of existing methods, ii) provides a detailed description of the evaluation protocols(i. e., datasets and metrics) to be used in TSGV, and iii) in-depth discusses potential problems of current benchmarking designs and research directions for further investigations.
Unsupervised Visual Program Induction with Function Modularization
Program induction serves as one way to analog the ability of human thinking.
Provable hierarchical lifelong learning with a sketch-based modular architecture
We propose a modular architecture for lifelong learning of hierarchically structured tasks.
A HYPOTHESIS FOR THE COGNITIVE DIFFICULTY OF IMAGES
This paper proposes a hypothesis to analyze the underlying reason for the cognitive difficulty of an image from two perspectives, i. e. a cognitive image usually makes a DNN strongly activated by cognitive concepts; discarding massive non-cognitive concepts may also help the DNN focus on cognitive concepts.
Evaluation of Various Open-Set Medical Imaging Tasks with Deep Neural Networks
The current generation of deep neural networks has achieved close-to-human results on "closed-set" image recognition; that is, the classes being evaluated overlap with the training classes.
Data-driven Control of Dynamic Event-triggered Systems with Delays
Data-based representations for time-invariant linear systems with known or unknown system input matrices are first developed, along with a novel class of dynamic triggering schemes for sampled-data systems with time delays.
CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks
In this paper, we investigate GNNs from the lens of weight and feature loss landscapes, i. e., the loss changes with respect to model weights and node features, respectively.
Hierarchical Knowledge Guided Learning for Real-world Retinal Diseases Recognition
From a modeling perspective, most deep learning models trained on these datasets may lack the ability to generalize to rare diseases where only a few available samples are presented for training.
Graph Differentiable Architecture Search with Structure Learning
Extensive experiments on real-world graph datasets demonstrate that our proposed GASSO model is able to achieve state-of-the-art performance compared with existing baselines.
Disentangled Contrastive Learning on Graphs
Then we propose a novel factor-wise discrimination objective in a contrastive learning manner, which can force the factorized representations to independently reflect the expressive information from different latent factors.
HybridGazeNet: Geometric model guided Convolutional Neural Networks for gaze estimation
As a critical cue for understanding human intention, human gaze provides a key signal for Human-Computer Interaction(HCI) applications.
Generalized Natural Language Grounded Navigation via Environment-agnostic Multitask Learning
Recent research efforts enable study for natural language grounded navigation in photo-realistic environments, e. g., following natural language instructions or dialog.
Exploring the Correlation between Likelihood of Flow-based Generative Models and Image Semantics
In this paper, we explore the correlation between flows' likelihood and image semantics.
Reject Illegal Inputs: Scaling Generative Classifiers with Supervised Deep Infomax
The supervised probabilistic constraints are equivalent to a generative classifier on high-level data representations, where class conditional log-likelihoods of samples can be evaluated.
Dynamic parameter reallocation improves trainability of deep convolutional networks
Network pruning has emerged as a powerful technique for reducing the size of deep neural networks.
OOD-GNN: Out-of-Distribution Generalized Graph Neural Network
Our proposed OOD-GNN employs a novel nonlinear graph representation decorrelation method utilizing random Fourier features, which encourages the model to eliminate the statistical dependence between relevant and irrelevant graph representations through iteratively optimizing the sample graph weights and graph encoder.
Intraspecific predator interference promotes biodiversity in ecosystems
Explaining biodiversity is a fundamental issue in ecology.
You Can Wash Better: Daily Handwashing Assessment with Smartwatches
We propose UWash, an intelligent solution upon smartwatches, to assess handwashing for the purpose of raising users' awareness and cultivating habits in high-quality handwashing.
Decentralized Stochastic Proximal Gradient Descent with Variance Reduction over Time-varying Networks
By transforming our decentralized algorithm into a centralized inexact proximal gradient algorithm with variance reduction, and controlling the bounds of error sequences, we prove that DPSVRG converges at the rate of $O(1/T)$ for general convex objectives plus a non-smooth term with $T$ as the number of iterations, while DSPG converges at the rate $O(\frac{1}{\sqrt{T}})$.
A Scalable Deep Reinforcement Learning Model for Online Scheduling Coflows of Multi-Stage Jobs for High Performance Computing
Coflow is a recently proposed networking abstraction to help improve the communication performance of data-parallel computing jobs.
Revisiting Transformation Invariant Geometric Deep Learning: Are Initial Representations All You Need?
Based on the experimental results, we advocate that TinvNN should be considered a new starting point and an essential baseline for further studies of transformation-invariant geometric deep learning.
Compression-Resistant Backdoor Attack against Deep Neural Networks
After training, the backdoor attack against DNN is robust to image compression.
Self-directed Machine Learning
Inspired by the concept of self-directed human learning, we introduce the principal concept of Self-directed Machine Learning (SDML) and propose a framework for SDML.
Adaptive Worker Grouping For Communication-Efficient and Straggler-Tolerant Distributed SGD
Wall-clock convergence time and communication load are key performance metrics for the distributed implementation of stochastic gradient descent (SGD) in parameter server settings.
Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation
Experiments over publicly available datasets demonstrate that our method can help models generate better responses, even such training data are usually impressed as low-quality data.
GAN-generated Faces Detection: A Survey and New Perspectives
Generative Adversarial Networks (GAN) have led to the generation of very realistic face images, which have been used in fake social media accounts and other disinformation matters that can generate profound impacts.
Model-Based and Data-Driven Control of Event- and Self-Triggered Discrete-Time LTI Systems
To this end, we begin by presenting a dynamic event-triggering scheme (ETS) based on periodic sampling, and a discrete-time looped-functional approach, through which a model-based stability condition is derived.
Curriculum Meta-Learning for Next POI Recommendation
Next point-of-interest (POI) recommendation is a hot research field where a recent emerging scenario, next POI to search recommendation, has been deployed in many online map services such as Baidu Maps.
Synergistic Network Learning and Label Correction for Noise-robust Image Classification
Taking the expertise of DNNs to learn meaningful patterns before fitting noise, our framework first trains two networks over the current dataset with small loss selection.
Optimal quantum dataset for learning a unitary transformation
In this work, we solve the problem on the minimum size of sufficient quantum datasets for learning a unitary transformation exactly, which reveals the power and limitation of quantum data.
Compilable Neural Code Generation with Compiler Feedback
Automatically generating compilable programs with (or without) natural language descriptions has always been a touchstone problem for computational linguistics and automated software engineering.
A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach
New benchmarking results indicate that our proposed evaluation protocols can better monitor the research progress.
Energy-Efficient UAV-Mounted RIS Assisted Mobile Edge Computing
Unmanned aerial vehicle (UAV) and reconfigurable intelligent surface (RIS) have been recently applied in the field of mobile edge computing (MEC) to improve the data exchange environment by proactively changing the wireless channels through maneuverable location deployment and intelligent signals reflection, respectively.
Flexible Sampling for Long-tailed Skin Lesion Classification
To address this, in this paper, we propose a curriculum learning-based framework called Flexible Sampling for the long-tailed skin lesion classification task.
The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterance
Since the short spoofed speech segments to be embedded by attackers are of variable length, six different temporal resolutions are considered, ranging from as short as 20 ms to as large as 640 ms. Third, we propose a new CM that enables the simultaneous use of the segment-level labels at different temporal resolutions as well as utterance-level labels to execute utterance- and segment-level detection at the same time.
A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes
In this paper, we propose a dynamic cascaded encoder Automatic Speech Recognition (ASR) model, which unifies models for different deployment scenarios.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Receiver Design for MIMO Unsourced Random Access with SKP Coding
In this letter, we extend the sparse Kronecker-product (SKP) coding scheme, originally designed for the additive white Gaussian noise (AWGN) channel, to multiple input multiple output (MIMO) unsourced random access (URA).
CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training
Specifically, we first extract multiple code views using compiler tools, and learn the complementary information among them under a contrastive learning framework.
Fundamental limitations on optimization in variational quantum algorithms
Exploring quantum applications of near-term quantum devices is a rapidly growing field of quantum information science with both theoretical and practical interests.
An Edge-Cloud Integrated Framework for Flexible and Dynamic Stream Analytics
In this paper, we study how to best leverage edge and cloud resources to achieve better accuracy and latency for stream analytics using a type of RNN model called long short-term memory (LSTM).
OIE@OIA: an Adaptable and Efficient Open Information Extraction Framework
OIE@OIA follows the methodology of Open Information eXpression (OIX): parsing a sentence to an Open Information Annotation (OIA) Graph and then adapting the OIA graph to different OIE tasks with simple rules.
Open-Eye: An Open Platform to Study Human Performance on Identifying AI-Synthesized Faces
In this work, we develop an online platform called Open-eye to study the human performance of AI-synthesized face detection.
Power and limitations of single-qubit native quantum neural networks
Quantum neural networks (QNNs) have emerged as a leading strategy to establish applications in machine learning, chemistry, and optimization.
Spatial Attention-based Implicit Neural Representation for Arbitrary Reduction of MRI Slice Spacing
Magnetic resonance (MR) images collected in 2D clinical protocols typically have large inter-slice spacing, resulting in high in-plane resolution and reduced through-plane resolution.
Mitigating barren plateaus of variational quantum eigensolvers
Variational quantum algorithms (VQAs) are expected to establish valuable applications on near-term quantum computers.
BInGo: Bayesian Intrinsic Groupwise Registration via Explicit Hierarchical Disentanglement
Multimodal groupwise registration aligns internal structures in a group of medical images.
Deep Learning-based Massive MIMO CSI Acquisition for 5G Evolution and 6G
Considering its large impact on air-interface design, it will be a candidate technology for 6th generation (6G) networks, in which an air interface designed by artificial intelligence can be used.
Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification
Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resources, restricting their success to domains where such resources are available.
Concentration of Data Encoding in Parameterized Quantum Circuits
This result in particular implies that the average encoded state will concentrate on the maximally mixed state at an exponential speed on depth.
Enhanced brain structure-function tethering in transmodal cortex revealed by high-frequency eigenmodes
Specifically, low-frequency eigenmodes, which are considered sufficient to capture the essence of the functional network, contribute little to functional connectivity reconstruction in transmodal regions, resulting in structure-function decoupling along the unimodal-transmodal gradient.
Rank-based Decomposable Losses in Machine Learning: A Survey
Following these categories, we review the literature on rank-based aggregate losses and rank-based individual losses.
Scene Recognition with Objectness, Attribute and Category Learning
Based on the complementarity of attribute and category labels, we propose a Multi-task Attribute-Scene Recognition (MASR) network which learns a category embedding and at the same time predicts scene attributes.
Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferability
This paper summarizes the common mechanism shared by twelve previous transferability-boosting methods in a unified view, i. e., these methods all reduce game-theoretic interactions between regional adversarial perturbations.
Trajectory Planning of Cellular-Connected UAV for Communication-assisted Radar Sensing
Being a key technology for beyond fifth-generation wireless systems, joint communication and radar sensing (JCAS) utilizes the reflections of communication signals to detect foreign objects and deliver situational awareness.
Event-triggered Consensus Control of Heterogeneous Multi-agent Systems: Model- and Data-based Analysis
This article deals with model- and data-based consensus control of heterogenous leader-following multi-agent systems (MASs) under an event-triggering transmission scheme.
A Theoretical View on Sparsely Activated Networks
After representing LSH-based sparse networks with our model, we prove that sparse networks can match the approximation power of dense networks on Lipschitz functions.
