Search Results for author:
Found 392 papers, 132 papers with code
Dependency Position Encoding for Relation Extraction
Leveraging the dependency tree of the input sentence is able to improve the model performance for relation extraction.
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.
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.
Deep Reinforcement Learning for Image-to-Image Translation
The key feature in the RL-I2IT framework is to decompose a monolithic learning process into small steps with a lightweight model to progressively transform a source image successively to a target image.
WiCV@CVPR2023: The Eleventh Women In Computer Vision Workshop at the Annual CVPR Conference
In this paper, we present the details of Women in Computer Vision Workshop - WiCV 2023, organized alongside the hybrid CVPR 2023 in Vancouver, Canada.
On-the-Fly SfM: What you capture is What you get
Over the last decades, ample achievements have been made on Structure from motion (SfM).
For A More Comprehensive Evaluation of 6DoF Object Pose Tracking
The limitations of previous scoring methods and error metrics are analyzed, based on which we introduce our improved evaluation methods.
Can large-scale vocoded spoofed data improve speech spoofing countermeasure with a self-supervised front end?
While many datasets use spoofed data generated by speech synthesis systems, it was recently found that data vocoded by neural vocoders were also effective as the spoofed training data.
Outlier Robust Adversarial Training
Theoretically, we show that the learning objective of ORAT satisfies the $\mathcal{H}$-consistency in binary classification, which establishes it as a proper surrogate to adversarial 0/1 loss.
Control-Oriented Modeling and Layer-to-Layer Spatial Control of Powder Bed Fusion Processes
However, due to inherent process variability, it is still very costly and time consuming to certify the process and the part.
DRAG: Divergence-based Adaptive Aggregation in Federated learning on Non-IID Data
Local stochastic gradient descent (SGD) is a fundamental approach in achieving communication efficiency in Federated Learning (FL) by allowing individual workers to perform local updates.
BenchTemp: A General Benchmark for Evaluating Temporal Graph Neural Networks
To handle graphs in which features or connectivities are evolving over time, a series of temporal graph neural networks (TGNNs) have been proposed.
Large Graph Models: A Perspective
Large models have emerged as the most recent groundbreaking achievements in artificial intelligence, and particularly machine learning.
A Survey on Fairness in Large Language Models
Then, for large-scale LLMs, we introduce recent fairness research, including fairness evaluation, reasons for bias, and debiasing methods.
Unsupervised Multiplex Graph Learning with Complementary and Consistent Information
Unsupervised multiplex graph learning (UMGL) has been shown to achieve significant effectiveness for different downstream tasks by exploring both complementary information and consistent information among multiple graphs.
SphereNet: Learning a Noise-Robust and General Descriptor for Point Cloud Registration
However, most methods are susceptible to noise and have poor generalization ability on unseen datasets.
Mixed-Precision Quantization with Cross-Layer Dependencies
Quantization assigning the same bit-width to all layers leads to large accuracy degradation at low precision and is wasteful at high precision settings.
DisAsymNet: Disentanglement of Asymmetrical Abnormality on Bilateral Mammograms using Self-adversarial Learning
The question of 'what the symmetrical Bi-MG would look like when the asymmetrical abnormalities have been removed ?'
Bridge the Performance Gap in Peak-hour Series Forecasting: The Seq2Peak Framework
Peak-Hour Series Forecasting (PHSF) is a crucial yet underexplored task in various domains.
Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases
Meanwhile, experimental results on the GLUE benchmark show that CCPA retains the language modeling capability of PLMs.
SageFormer: Series-Aware Graph-Enhanced Transformers for Multivariate Time Series Forecasting
Multivariate time series forecasting plays a critical role in diverse domains.
Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directions
The development of applications based on artificial intelligence and implemented over wireless networks is increasingly rapidly and is expected to grow dramatically in the future.
An Explainable Deep Framework: Towards Task-Specific Fusion for Multi-to-One MRI Synthesis
Multi-sequence MRI is valuable in clinical settings for reliable diagnosis and treatment prognosis, but some sequences may be unusable or missing for various reasons.
Synthesis of Contrast-Enhanced Breast MRI Using Multi-b-Value DWI-based Hierarchical Fusion Network with Attention Mechanism
DWIs with different b-values are fused to efficiently utilize the difference features of DWIs.
Textbooks Are All You Need
Despite this small scale, phi-1 attains pass@1 accuracy 50. 6% on HumanEval and 55. 5% on MBPP.
Ranked #12 on
Code Generation
on HumanEval
Efficient Search and Detection of Relevant Plant Parts using Semantics-Aware Active Vision
To automate harvesting and de-leafing of tomato plants using robots, it is important to search and detect the relevant plant parts, namely tomatoes, peduncles, and petioles.
Towards single integrated spoofing-aware speaker verification embeddings
Second, competitive performance should be demonstrated compared to the fusion of automatic speaker verification (ASV) and countermeasure (CM) embeddings, which outperformed single embedding solutions by a large margin in the SASV2022 challenge.
Controllable Text-to-Image Generation with GPT-4
Control-GPT works by querying GPT-4 to write TikZ code, and the generated sketches are used as references alongside the text instructions for diffusion models (e. g., ControlNet) to generate photo-realistic images.
Range-Based Equal Error Rate for Spoof Localization
To properly measure misclassified ranges and better evaluate spoof localization performance, we upgrade point-based EER to range-based EER.
Integrating Listwise Ranking into Pairwise-based Image-Text Retrieval
Given a query caption, the goal is to rank candidate images by relevance, from large to small.
WeiAvg: Federated Learning Model Aggregation Promoting Data Diversity
Federated learning provides a promising privacy-preserving way for utilizing large-scale private edge data from massive Internet-of-Things (IoT) devices.
TOAST: Transfer Learning via Attention Steering
We introduce Top-Down Attention Steering (TOAST), a novel transfer learning algorithm that keeps the pre-trained backbone frozen, selects task-relevant features in the output, and feeds those features back to the model to steer the attention to the task-specific features.
Gorilla: Large Language Model Connected with Massive APIs
Large Language Models (LLMs) have seen an impressive wave of advances recently, with models now excelling in a variety of tasks, such as mathematical reasoning and program synthesis.
Improving Generalization Ability of Countermeasures for New Mismatch Scenario by Combining Multiple Advanced Regularization Terms
The ability of countermeasure models to generalize from seen speech synthesis methods to unseen ones has been investigated in the ASVspoof challenge.
Efficient information recovery from Pauli noise via classical shadow
The rapid advancement of quantum computing has led to an extensive demand for effective techniques to extract classical information from quantum systems, particularly in fields like quantum machine learning and quantum chemistry.
Clothes Grasping and Unfolding Based on RGB-D Semantic Segmentation
These methods often utilize physics engines to synthesize depth images to reduce the cost of real labeled data collection.
DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation
To tackle the problems, we propose DisenBooth, an identity-preserving disentangled tuning framework for subject-driven text-to-image generation in this paper.
DELTA: Dynamic Embedding Learning with Truncated Conscious Attention for CTR Prediction
To tackle this problem, inspired by the Global Workspace Theory in conscious processing, which posits that only a specific subset of the product features are pertinent while the rest can be noisy and even detrimental to human-click behaviors, we propose a CTR model that enables Dynamic Embedding Learning with Truncated Conscious Attention for CTR prediction, termed DELTA.
An Implicit Alignment for Video Super-Resolution
Video super-resolution commonly uses a frame-wise alignment to support the propagation of information over time.
Ranked #1 on
Video Super-Resolution
on REDS4- 4x upscaling
JaxPruner: A concise library for sparsity research
This paper introduces JaxPruner, an open-source JAX-based pruning and sparse training library for machine learning research.
LayerNAS: Neural Architecture Search in Polynomial Complexity
For a model architecture with $L$ layers, we perform layerwise-search for each layer, selecting from a set of search options $\mathbb{S}$.
Harnessing the Power of Text-image Contrastive Models for Automatic Detection of Online Misinformation
As growing usage of social media websites in the recent decades, the amount of news articles spreading online rapidly, resulting in an unprecedented scale of potentially fraudulent information.
USNID: A Framework for Unsupervised and Semi-supervised New Intent Discovery
New intent discovery is of great value to natural language processing, allowing for a better understanding of user needs and providing friendly services.
Arbitrary Reduction of MRI Inter-slice Spacing Using Hierarchical Feature Conditional Diffusion
Magnetic resonance (MR) images collected in 2D scanning protocols typically have large inter-slice spacing, resulting in high in-plane resolution but reduced through-plane resolution.
Adversarially Robust Neural Architecture Search for Graph Neural Networks
To tackle these challenges, we propose a novel Robust Neural Architecture search framework for GNNs (G-RNA).
CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions
The core of this dataset is a blending optimization process, which corrects for the pose as it drifts and is affected by the magnetic conditions.
Domain Adaptive Semantic Segmentation by Optimal Transport
Second, we utilize OT to achieve a more robust alignment of source and target domains in output space, where the OT plan defines a well attention mechanism to improve the adaptation of the model.
Damage detection of high-speed railway box girder using train-induced dynamic responses
This paper proposes a damage detection method based on the train-induced responses of high-speed railway box girder.
Top-Down Visual Attention from Analysis by Synthesis
In this paper, we consider top-down attention from a classic Analysis-by-Synthesis (AbS) perspective of vision.
A Survey of Graph Prompting Methods: Techniques, Applications, and Challenges
In particular, we introduce the basic concepts of graph prompt learning, organize the existing work of designing graph prompting functions, and describe their applications and future challenges.
Optimal Beamforming for MIMO DFRC Systems with Transmit Covariance Constraints
Under this approach, we reveal that the optimal receive beamforming is given by the classic MMSE one and the optimal transmit beamforming design amounts to solving an orthogonal Procrustes problem, thereby allowing for closed-form solutions to subproblems in each BCD step and fast convergence of the proposed algorithm to a high-quality (near-optimal) overall beamforming design.
Selectively Hard Negative Mining for Alleviating Gradient Vanishing in Image-Text Matching
To alleviate the gradient vanishing problem, we propose a Selectively Hard Negative Mining (SelHN) strategy, which chooses whether to mine hard negative samples according to the gradient vanishing condition.
RIS-Assisted Jamming Rejection and Path Planning for UAV-Borne IoT Platform: A New Deep Reinforcement Learning Framework
This paper presents a new deep reinforcement learning (DRL)-based approach to the trajectory planning and jamming rejection of an unmanned aerial vehicle (UAV) for the Internet-of-Things (IoT) applications.
Unsupervised Deep Learning for IoT Time Series
IoT time series analysis has found numerous applications in a wide variety of areas, ranging from health informatics to network security.
Curriculum Graph Machine Learning: A Survey
To the best of our knowledge, this paper is the first survey for curriculum graph machine learning.
IMPORTANT-Net: Integrated MRI Multi-Parameter Reinforcement Fusion Generator with Attention Network for Synthesizing Absent Data
Then the multi-parameter fusion with attention module enables the interaction of the encoded information from different parameters through a set of algorithmic strategies, and applies different weights to the information through the attention mechanism after information fusion to obtain refined representation information.
Synthesis-based Imaging-Differentiation Representation Learning for Multi-Sequence 3D/4D MRI
Multi-sequence MRIs can be necessary for reliable diagnosis in clinical practice due to the complimentary information within sequences.
The Power of External Memory in Increasing Predictive Model Capacity
One way of introducing sparsity into deep networks is by attaching an external table of parameters that is sparsely looked up at different layers of the network.
Alternating Updates for Efficient Transformers
We introduce Alternating Updates (AltUp), a simple-to-implement method to increase a model's capacity without the computational burden.
Attacking Important Pixels for Anchor-free Detectors
Existing adversarial attacks on object detection focus on attacking anchor-based detectors, which may not work well for anchor-free detectors.
You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement
The Retinex-based methods require decomposing the image into reflectance and illumination components, which is a highly ill-posed problem and there is no available ground truth.
Understanding Zero-Shot Adversarial Robustness for Large-Scale Models
We apply this training loss to two adaption methods, model finetuning and visual prompt tuning.
Doubly Right Object Recognition: A Why Prompt for Visual Rationales
We propose a ``doubly right'' object recognition benchmark, where the metric requires the model to simultaneously produce both the right labels as well as the right rationales.
Hiding speaker's sex in speech using zero-evidence speaker representation in an analysis/synthesis pipeline
The use of modern vocoders in an analysis/synthesis pipeline allows us to investigate high-quality voice conversion that can be used for privacy purposes.
Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation
In our DA framework, we retain the depth and background information during the domain feature alignment.
Disentangled Representation Learning
Disentangled Representation Learning (DRL) aims to learn a model capable of identifying and disentangling the underlying factors hidden in the observable data in representation form.
FedSiam-DA: Dual-aggregated Federated Learning via Siamese Network under Non-IID Data
Federated learning is a distributed learning that allows each client to keep the original data locally and only upload the parameters of the local model to the server.
Superresolution Reconstruction of Single Image for Latent features
Therefore, it is often challenging to meet the requirements of High-quality sampling, fast Sampling, and diversity of details and texture after Sampling simultaneously in a SISR task. It leads to model collapse, lack of details and texture features after Sampling, and too long Sampling time in High Resolution (HR) image reconstruction methods.
Shared Loss between Generators of GANs
Traditional GANs fall prey to the mode collapse problem, which means that they are unable to generate the different variations of data present in the input dataset.
LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation
We propose LiDAL, a novel active learning method for 3D LiDAR semantic segmentation by exploiting inter-frame uncertainty among LiDAR frames.
Large Language Models with Controllable Working Memory
By contrast, when the context is irrelevant to the task, the model should ignore it and fall back on its internal knowledge.
Lightweight Neural Network with Knowledge Distillation for CSI Feedback
Firstly, an autoencoder KD-based method is introduced by training a student autoencoder to mimic the reconstructed CSI of a pretrained teacher autoencoder.
Detection of Real-time DeepFakes in Video Conferencing with Active Probing and Corneal Reflection
Specifically, we authenticate video calls by displaying a distinct pattern on the screen and using the corneal reflection extracted from the images of the call participant's face.
RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control
Reinforcement learning is applied to solve actual complex tasks from high-dimensional, sensory inputs.
Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoders
To make better use of pairs of bona fide and spoofed data, this study introduces a contrastive feature loss that can be plugged into the standard training criterion.
InFIP: An Explainable DNN Intellectual Property Protection Method based on Intrinsic Features
Since the intrinsic feature is composed of unique interpretation of the model's decision, the intrinsic feature can be regarded as fingerprint of the model.
GGViT:Multistream Vision Transformer Network in Face2Face Facial Reenactment Detection
The compression of videos on social media has destroyed some pixel details that could be used to detect forgeries.
Block Format Error Bounds and Optimal Block Size Selection
This measure allows us to determine the optimal parameters, such as the block size, yielding highest accuracy.
3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography
In this work, we introduce the image matting into the 3D scenes and use the alpha matte, i. e., a soft mask, to describe lesions in a 3D medical image.
STSyn: Speeding Up Local SGD with Straggler-Tolerant Synchronization
Synchronous local stochastic gradient descent (local SGD) suffers from some workers being idle and random delays due to slow and straggling workers, as it waits for the workers to complete the same amount of local updates.
Attention Augmented ConvNeXt UNet For Rectal Tumour Segmentation
It is a challenge to segment the location and size of rectal cancer tumours through deep learning.
Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval
More specifically, Triplet loss with Hard Negative mining (Triplet-HN), which is widely used in existing retrieval models to improve the discriminative ability, is easy to fall into local minima in training.
3D Matting: A Soft Segmentation Method Applied in Computed Tomography
It can be caused by many factors, such as the imaging properties, pathological anatomy, and the weak representation of the binary masks, which brings challenges to accurate 3D segmentation.
MIntRec: A New Dataset for Multimodal Intent Recognition
This paper introduces a novel dataset for multimodal intent recognition (MIntRec) to address this issue.
Ranked #1 on
Multimodal Intent Recognition
on MIntRec
Joint Speaker Encoder and Neural Back-end Model for Fully End-to-End Automatic Speaker Verification with Multiple Enrollment Utterances
Conventional automatic speaker verification systems can usually be decomposed into a front-end model such as time delay neural network (TDNN) for extracting speaker embeddings and a back-end model such as statistics-based probabilistic linear discriminant analysis (PLDA) or neural network-based neural PLDA (NPLDA) for similarity scoring.
NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results
We present the design and baseline results for a new challenge in the ChaLearn meta-learning series, accepted at NeurIPS'22, focusing on "cross-domain" meta-learning.
NL2GDPR: Automatically Develop GDPR Compliant Android Application Features from Natural Language
At the core, NL2GDPR is a privacy-centric information extraction model, appended with a GDPR policy finder and a policy generator.
Data-Driven Control of Distributed Event-Triggered Network Systems
The present paper deals with data-driven event-triggered control of a class of unknown discrete-time interconnected systems (a. k. a.
Context-Aware Streaming Perception in Dynamic Environments
These works evaluate accuracy offline, one image at a time.
Efficient Climate Simulation via Machine Learning Method
We develop a user-friendly platform NeuroGCM for efficiently developing hybrid modeling in climate simulation.
GPPT: Graph Pre-training and Prompt Tuning to Generalize Graph Neural Networks
Based on the pre-trained model, we propose the graph prompting function to modify the standalone node into a token pair, and reformulate the downstream node classification looking the same as edge prediction.
Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classification
Graph neural networks (GNNs) have achieved tremendous success in the task of graph classification and its diverse downstream real-world applications.
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.
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.
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.
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.
PanGu-Coder: Program Synthesis with Function-Level Language Modeling
We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i. e. the synthesis of programming language solutions given a natural language problem description.
Neural-Sim: Learning to Generate Training Data with NeRF
However, existing approaches either require human experts to manually tune each scene property or use automatic methods that provide little to no control; this requires rendering large amounts of random data variations, which is slow and is often suboptimal for the target domain.
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.
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.
Scaling Novel Object Detection with Weakly Supervised Detection Transformers
A critical object detection task is finetuning an existing model to detect novel objects, but the standard workflow requires bounding box annotations which are time-consuming and expensive to collect.
Unsupervised Domain Adaptive Fundus Image Segmentation with Category-level Regularization
Existing unsupervised domain adaptation methods based on adversarial learning have achieved good performance in several medical imaging tasks.
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.
NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search
To the best of our knowledge, our work is the first benchmark for graph neural architecture search.
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.
A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions
Motivated by the tremendous success of deep learning in clustering, one of the most fundamental machine learning tasks, and the large number of recent advances in this direction, in this paper we conduct a comprehensive survey on deep clustering by proposing a new taxonomy of different state-of-the-art approaches.
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.
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.
BInGo: Bayesian Intrinsic Groupwise Registration via Explicit Hierarchical Disentanglement
Multimodal groupwise registration aligns internal structures in a group of medical images.
Mitigating barren plateaus of variational quantum eigensolvers
Variational quantum algorithms (VQAs) are expected to establish valuable applications on near-term quantum computers.
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.
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.
The VoicePrivacy 2020 Challenge Evaluation Plan
The VoicePrivacy Challenge aims to promote the development of privacy preservation tools for speech technology by gathering a new community to define the tasks of interest and the evaluation methodology, and benchmarking solutions through a series of challenges.
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.
Quantum Self-Attention Neural Networks for Text Classification
Although some efforts based on syntactic analysis have opened the door to research in Quantum NLP (QNLP), limitations such as heavy syntactic preprocessing and syntax-dependent network architecture make them impracticable on larger and real-world data sets.
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).
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.
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).
Visual Attention Emerges from Recurrent Sparse Reconstruction
We present VARS, Visual Attention from Recurrent Sparse reconstruction, a new attention formulation built on two prominent features of the human visual attention mechanism: recurrency and sparsity.
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
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.
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.
Learning to Solve Travelling Salesman Problem with Hardness-adaptive Curriculum
To solve these challenges, we first propose a principled hardness measurement to quantify the hardness of TSP instances.
Investigating Active-learning-based Training Data Selection for Speech Spoofing Countermeasure
This study took the initiative and investigated CM training using active learning (AL), a framework that iteratively selects useful data from a large pool set and fine-tunes the CM.
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.
The VoicePrivacy 2022 Challenge Evaluation Plan
Participants apply their developed anonymization systems, run evaluation scripts and submit objective evaluation results and anonymized speech data to the organizers.
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.
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.
Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild
Building reliable object detectors that can detect out-of-distribution (OOD) objects is critical yet underexplored.
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.
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.
Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation
The performance of spoofing countermeasure systems depends fundamentally upon the use of sufficiently representative training data.
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.
Out-Of-Distribution Generalization on Graphs: A Survey
This paper is the first systematic and comprehensive review of OOD generalization on graphs, to the best of our knowledge.
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.
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.
Dichotomic Pattern Mining with Applications to Intent Prediction from Semi-Structured Clickstream Datasets
We introduce a pattern mining framework that operates on semi-structured datasets and exploits the dichotomy between outcomes.
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.
Robust Contrastive Learning against Noisy Views
Contrastive learning relies on an assumption that positive pairs contain related views, e. g., patches of an image or co-occurring multimodal signals of a video, that share certain underlying information about an instance.
A Practical Guide to Logical Access Voice Presentation Attack Detection
Presentation attack detection (PAD) for ASV, or speech anti-spoofing, is therefore indispensable.
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.
Automated Graph Machine Learning: Approaches, Libraries and Directions
Graph machine learning has been extensively studied in both academic and industry.
Compression-Resistant Backdoor Attack against Deep Neural Networks
After training, the backdoor attack against DNN is robust to image compression.
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.
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.
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 $O(\frac{1}{\sqrt{T}})$.
Reproducible and Portable Big Data Analytics in the Cloud
To tackle these problems, we leverage serverless computing and containerization techniques for automated scalable execution and reproducibility, and utilize the adapter design pattern to enable application portability and reproducibility across different clouds.
Stochastic Actor-Executor-Critic for Image-to-Image Translation
Training a model-free deep reinforcement learning model to solve image-to-image translation is difficult since it involves high-dimensional continuous state and action spaces.
Stochastic Planner-Actor-Critic for Unsupervised Deformable Image Registration
We evaluate our method on several 2D and 3D medical image datasets, some of which contain large deformations.
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.
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.
Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness
This paper provides a unified view to explain different adversarial attacks and defense methods, i. e. the view of multi-order interactions between input variables of DNNs.
Curriculum Disentangled Recommendation with Noisy Multi-feedback
However, learning such disentangled representations from multi-feedback data is challenging because i) multi-feedback is complex: there exist complex relations among different types of feedback (e. g., click, unclick, and dislike, etc) as well as various user intentions, and ii) multi-feedback is noisy: there exists noisy (useless) information both in features and labels, which may deteriorate the recommendation performance.
Not All Low-Pass Filters are Robust in Graph Convolutional Networks
Graph Convolutional Networks (GCNs) are promising deep learning approaches in learning representations for graph-structured data.
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.
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.
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.
Active Learning Meets Optimized Item Selection
Designing recommendation systems with limited or no available training data remains a challenge.
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.
Investigating self-supervised front ends for speech spoofing countermeasures
Self-supervised speech model is a rapid progressing research topic, and many pre-trained models have been released and used in various down stream tasks.
A Unified Game-Theoretic Interpretation of Adversarial Robustness
This paper provides a unified view to explain different adversarial attacks and defense methods, \emph{i. e.} the view of multi-order interactions between input variables of DNNs.
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.
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.
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.
Efficiently Solve the Max-cut Problem via a Quantum Qubit Rotation Algorithm
The quantum circuits are comprised with single-qubit rotation gates implementing on each qubit.
Estimating the confidence of speech spoofing countermeasure
On the ASVspoof2019 logical access database, the results demonstrate that an energy-based estimator and a neural-network-based one achieved acceptable performance in identifying unknown attacks in the test set.
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.