Search Results for author:
Found 135 papers, 41 papers with code
Eye Gaze and Self-attention: How Humans and Transformers Attend Words in Sentences
Attention describes cognitive processes that are important to many human phenomena including reading.
UniIR: Training and Benchmarking Universal Multimodal Information Retrievers
Existing information retrieval (IR) models often assume a homogeneous format, limiting their applicability to diverse user needs, such as searching for images with text descriptions, searching for a news article with a headline image, or finding a similar photo with a query image.
Automatic Identification of Driving Maneuver Patterns using a Robust Hidden Semi-Markov Models
There is an increase in interest to model driving maneuver patterns via the automatic unsupervised clustering of naturalistic sequential kinematic driving data.
Control3D: Towards Controllable Text-to-3D Generation
In particular, a 2D conditioned diffusion model (ControlNet) is remoulded to guide the learning of 3D scene parameterized as NeRF, encouraging each view of 3D scene aligned with the given text prompt and hand-drawn sketch.
3DStyle-Diffusion: Pursuing Fine-grained Text-driven 3D Stylization with 2D Diffusion Models
In this work, we propose a new 3DStyle-Diffusion model that triggers fine-grained stylization of 3D meshes with additional controllable appearance and geometric guidance from 2D Diffusion models.
Large Language Models Illuminate a Progressive Pathway to Artificial Healthcare Assistant: A Review
This has sparked significant interest in applying LLMs to enhance various aspects of healthcare, ranging from medical education to clinical decision support.
Reducing the impact of non-ideal PRBS on microwave photonic random demodulators by low biasing the optical modulator via PRBS amplitude compression
Different from the commonly used method that switches the bias point of the optical modulator in the RD between two quadrature transmission points to mix the signal to be sampled and the PRBS, this method employs a PRBS with lower amplitude to low bias the optical modulator so that the impact of non-ideal PRBS on microwave photonic RDs can be greatly reduced by compressing the amplitude of non-ideal parts of the PRBS.
Momentum Gradient-based Untargeted Attack on Hypergraph Neural Networks
We use a momentum gradient mechanism to choose the attack node features in the feature selection module.
A Systematic Evaluation of Large Language Models on Out-of-Distribution Logical Reasoning Tasks
We carry out experiments on these datasets with both discriminative and generative LLMs and show that these simple tricks greatly hinder the performance of the language models.
Deep Learning Predicts Biomarker Status and Discovers Related Histomorphology Characteristics for Low-Grade Glioma
Biomarker detection is an indispensable part in the diagnosis and treatment of low-grade glioma (LGG).
Can Language Models be Instructed to Protect Personal Information?
While data leaks should be prevented, it is also crucial to examine the trade-off between the privacy protection and model utility of proposed approaches.
Automated Bug Generation in the era of Large Language Models
From the classic software engineering point of view, a hard-to-repair bug differs from the correct code in multiple locations, making it hard to localize and repair.
HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image
Many studies adopt random sampling pre-processing strategy and WSI-level aggregation models, which inevitably lose critical prognostic information in the patient-level bag.
Lightweight wood panel defect detection method incorporating attention mechanism and feature fusion network
In recent years, deep learning has made significant progress in wood panel defect detection.
Meerkat Behaviour Recognition Dataset
Recording animal behaviour is an important step in evaluating the well-being of animals and further understanding the natural world.
JCCS-PFGM: A Novel Circle-Supervision based Poisson Flow Generative Model for Multiphase CECT Progressive Low-Dose Reconstruction with Joint Condition
Multiphase contrast-enhanced computed tomography (CECT) scan is clinically significant to demonstrate the anatomy at different phases.
Out-of-distribution forgetting: vulnerability of continual learning to intra-class distribution shift
In this work, we reported a special form of catastrophic forgetting raised by the OOD problem in continual learning settings, and we named it out-of-distribution forgetting (OODF).
Channelized analog microwave short-time Fourier transform in the optical domain with improved measurement performance
For the first time, channelization measurement technology is introduced in the STFT system based on frequency sweeping and FTTM, greatly reducing the frequency-sweep range of the required frequency-sweep signal to the analysis bandwidth divided by the number of channels.
Better Low-Resource Entity Recognition Through Translation and Annotation Fusion
Pre-trained multilingual language models have enabled significant advancements in cross-lingual transfer.
Cross-Lingual Transfer
Low Resource Named Entity Recognition
+4
Enhancing Logical Reasoning of Large Language Models through Logic-Driven Data Augmentation
Combining large language models with logical reasoning enhance their capacity to address problems in a robust and reliable manner.
Neuromodulation Gated Transformer
We introduce a novel architecture, the Neuromodulation Gated Transformer (NGT), which is a simple implementation of neuromodulation in transformers via a multiplicative effect.
Emergence of Symbols in Neural Networks for Semantic Understanding and Communication
The capacity to generate meaningful symbols and effectively employ them for advanced cognitive processes, such as communication, reasoning, and planning, constitutes a fundamental and distinctive aspect of human intelligence.
Boosting Verified Training for Robust Image Classifications via Abstraction
Via abstraction, all perturbed images are mapped into intervals before feeding into neural networks for training.
A Radiomics-Incorporated Deep Ensemble Learning Model for Multi-Parametric MRI-based Glioma Segmentation
Four deep neural networks as sub-models following the U-Net architecture were trained for the segmenting of a region-of-interest (ROI): each sub-model utilizes the mp-MRI and 1 of the 4 PCs as a 5-channel input for a 2D execution.
xASTNN: Improved Code Representations for Industrial Practice
The proposed xASTNN has three advantages.
Geometric Visual Similarity Learning in 3D Medical Image Self-supervised Pre-training
We propose a novel visual similarity learning paradigm, Geometric Visual Similarity Learning, which embeds the prior of topological invariance into the measurement of the inter-image similarity for consistent representation of semantic regions.
Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?
In this study, we introduce InfoSeek, a visual question answering dataset tailored for information-seeking questions that cannot be answered with only common sense knowledge.
Ranked #2 on
Visual Question Answering (VQA)
on InfoSeek
Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities
Large-scale multi-modal pre-training models such as CLIP and PaLI exhibit strong generalization on various visual domains and tasks.
Ranked #2 on
Fine-Grained Image Recognition
on OVEN
Learning Density-Based Correlated Equilibria for Markov Games
In real-world multi-agent systems, in addition to being in an equilibrium, agents' policies are often expected to meet requirements with respect to safety, and fairness.
MSDC: Exploiting Multi-State Power Consumption in Non-intrusive Load Monitoring based on A Dual-CNN Model
Non-intrusive load monitoring (NILM) aims to decompose aggregated electrical usage signal into appliance-specific power consumption and it amounts to a classical example of blind source separation tasks.
Alleviating Catastrophic Forgetting of Incremental Object Detection via Within-Class and Between-Class Knowledge Distillation
However, previous works on feature distillation heavily rely on low-level feature information, while under-exploring the importance of high-level semantic information.
LNPL-MIL: Learning from Noisy Pseudo Labels for Promoting Multiple Instance Learning in Whole Slide Image
Gigapixel Whole Slide Images (WSIs) aided patient diagnosis and prognosis analysis are promising directions in computational pathology.
Human-in-the-loop Evaluation for Early Misinformation Detection: A Case Study of COVID-19 Treatments
We present a human-in-the-loop evaluation framework for fact-checking novel misinformation claims and identifying social media messages that support them.
Incorporating Polar Field Data for Improved Solar Flare Prediction
In this paper, we consider incorporating data associated with the sun's north and south polar field strengths to improve solar flare prediction performance using machine learning models.
Frustratingly Easy Label Projection for Cross-lingual Transfer
Translating training data into many languages has emerged as a practical solution for improving cross-lingual transfer.
Ranked #1 on
Cross-Lingual NER
on MasakhaNER2.0
A case for disaggregation of ML data processing
Finally, we show that tf. data service advanced features can benefit performance of non-input bound jobs; in particular, coordinated data reads through tf. data service can yield up to 2x speedups and job cost savings for NLP jobs.
Robust prescribed-time coordination control of cooperative-antagonistic networks with disturbances
This article targets at addressing the robust prescribed-time coordination control (PTCC) problems for single-integrator cooperative-antagonistic networks (CANs) with external disturbances under arbitrary fixed signed digraphs without any structural constraints.
Prompt-based Conservation Learning for Multi-hop Question Answering
In this paper, we propose the Prompt-based Conservation Learning (PCL) framework for multi-hop QA, which acquires new knowledge from multi-hop QA tasks while conserving old knowledge learned on single-hop QA tasks, mitigating forgetting.
View Sub-sampling and Reconstruction for Efficient Light Field Compression
In this work, we study different sub-sampling and reconstruction strategies for light field compression.
Breaking the accuracy and resolution limitation of filter- and frequency-to-time mapping-based time and frequency acquisition methods by broadening the filter bandwidth
In this paper, the filter- and frequency-to-time mapping (FTTM)-based photonics-assisted time and frequency acquisition methods are comprehensively analyzed and the accuracy and resolution limitation in the fast sweep scenario is broken by broadening the filter bandwidth.
Photonics-assisted analog wideband self-interference cancellation for in-band full-duplex MIMO systems with adaptive digital amplitude and delay pre-matching
A photonics-assisted analog wideband RF self-interference (SI) cancellation and frequency downconversion approach for in-band full-duplex (IBFD) multiple-input multiple-output (MIMO) systems with adaptive digital amplitude and delay pre-matching is proposed based on a dual-parallel Mach-Zehnder modulator (DP-MZM).
Digitally-assisted photonic analog domain self-interference cancellation for in-band full-duplex MIMO systems via LS algorithm with adaptive order
The SIC and frequency downconversion are achieved in the optical domain via a dual-parallel Mach-Zehnder modulator (DP-MZM), while the downconverted signal is processed by the LS algorithm with adaptive order that is used to track the response of the multipath self-interference (SI) channel and reconstruct the reference signal for SIC.
Short-term Load Forecasting with Distributed Long Short-Term Memory
With the employment of smart meters, massive data on consumer behaviour can be collected by retailers.
MetaComp: Learning to Adapt for Online Depth Completion
However, facing a new environment where the test data occurs online and differs from the training data in the RGB image content and depth sparsity, the trained model might suffer severe performance drop.
Multiple Instance Learning with Mixed Supervision in Gleason Grading
We achieve the state-of-the-art performance on the SICAPv2 dataset, and the visual analysis shows the accurate prediction results of instance level.
Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation
Denoising Diffusion Probabilistic Model (DDPM) is able to make flexible conditional image generation from prior noise to real data, by introducing an independent noise-aware classifier to provide conditional gradient guidance at each time step of denoising process.
Ranked #1 on
Conditional Image Generation
on ImageNet 256x256
Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering
We then achieve the decomposition of a multi-hop question via segmentation of the corresponding AMR graph based on the required reasoning type.
Graph Fourier transform based on singular value decomposition of directed Laplacian
The proposed GFT is consistent with the conventional GFT in the undirected graph setting, and on directed circulant graphs, the proposed GFT is the classical discrete Fourier transform, up to some rotation, permutation and phase adjustment.
MNet: Rethinking 2D/3D Networks for Anisotropic Medical Image Segmentation
The nature of thick-slice scanning causes severe inter-slice discontinuities of 3D medical images, and the vanilla 2D/3D convolutional neural networks (CNNs) fail to represent sparse inter-slice information and dense intra-slice information in a balanced way, leading to severe underfitting to inter-slice features (for vanilla 2D CNNs) and overfitting to noise from long-range slices (for vanilla 3D CNNs).
WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma
According to the technical reports of the top-tier teams, CAM is still the most popular approach in WSSS.
Data Augmentation
Weakly supervised Semantic Segmentation
+1
Predicting Solar Flares Using CNN and LSTM on Two Solar Cycles of Active Region Data
We consider the flare prediction problem that distinguishes flare-imminent active regions that produce an M- or X-class flare in the future 24 hours, from quiet active regions that do not produce any flare within $\pm 24$ hours.
Individual-Level Inverse Reinforcement Learning for Mean Field Games
This limitation invalidates existing IRL methods on MFGs with non-cooperative environments.
Proximal PanNet: A Model-Based Deep Network for Pansharpening
To alleviate this issue, we propose a novel deep network for pansharpening by combining the model-based methodology with the deep learning method.
Photonics-Assisted Joint Communication-Radar System Based on a QPSK-Sliced Linearly Frequency-Modulated Signal
A photonics-assisted joint communication-radar system is proposed and experimentally demonstrated, by introducing a quadrature phase-shift keying (QPSK)-sliced linearly frequency-modulated (LFM) signal.
Time-varying microwave photonic filter for arbitrary waveform signal-to-noise ratio improvement
A time-varying microwave photonic filter (TV-MPF) based on stimulated Brillouin scattering (SBS) is proposed and utilized to suppress the in-band noise of broadband arbitrary microwave waveforms, thereby improving the signal-to-noise ratio (SNR).
Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learning
The progressive enhancement process facilitates the learning of discriminative features with fine-grained face forgery clues.
Transferrable Contrastive Learning for Visual Domain Adaptation
From this point, we present a particular paradigm of self-supervised learning tailored for domain adaptation, i. e., Transferrable Contrastive Learning (TCL), which links the SSL and the desired cross-domain transferability congruently.
A Style and Semantic Memory Mechanism for Domain Generalization
Correspondingly, we also propose a novel "jury" mechanism, which is particularly effective in learning useful semantic feature commonalities among domains.
Ranked #34 on
Domain Generalization
on PACS
Short-time Fourier transform based on stimulated Brillouin scattering
In the proposed all-optical STFT system, SBS not only provides a band-pass filter for implementing the window function in conjunction with a periodic frequency-sweep optical signal but also obtains the frequency domain information in different time windows through the generated waveform via frequency-to-time mapping (FTTM).
Photonics-based de-chirping and leakage cancellation for frequency-modulated continuous-wave radar system
The leakage cancellation scheme is used in a radar system.
Digital-assisted photonic analog wideband multipath self-interference cancellation
The proposed method can solve the performance limitation in the previously reported SIC methods of constructing the multipath SI signal using a single reference caused by the limited dynamic range of the digital-to-analog converter when the direct-path SI signal is much stronger than the sub-weak reflection-path SI signals.
Photonics-assisted wideband RF self-interference cancellation with digital domain amplitude and delay pre-matching
One dual-drive Mach-Zehnder modulator is used to implement the analog self-interference cancellation by pre-adjusting the delay and amplitude of the reference signal applied to the dual-drive Mach-Zehnder modulator in the digital domain.
Time-frequency analysis of microwave signals based on stimulated Brillouin scattering
The parallel SBS link can be utilized to perform real-time time-frequency analysis of microwave signal, which provides a promising solution for real-time time-frequency analysis, especially when it is combined with the photonic integration technique.
Spatiotemporal Inconsistency Learning for DeepFake Video Detection
To address this issue, we term this task as a Spatial-Temporal Inconsistency Learning (STIL) process and instantiate it into a novel STIL block, which consists of a Spatial Inconsistency Module (SIM), a Temporal Inconsistency Module (TIM), and an Information Supplement Module (ISM).
Photonic-enabled radio-frequency self-interference cancellation incorporated in an in-band full-duplex radio-over-fiber system
A photonic approach for radio-frequency (RF) self-interference cancellation (SIC) incorporated in an in-band full-duplex radio-over-fiber system is proposed.
Cross-Subject Domain Adaptation for Classifying Working Memory Load with Multi-Frame EEG Images
First, the Subject-Shared module in CS-DASA receives multi-frame EEG image data from both source and target subjects and learns the common feature representations.
EnMcGAN: Adversarial Ensemble Learning for 3D Complete Renal Structures Segmentation
3)We propose the adversarial weighted ensemble module which uses the trained discriminators to evaluate the quality of segmented structures, and normalizes these evaluation scores for the ensemble weights directed at the input image, thus enhancing the ensemble results.
TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification
Multiple instance learning (MIL) is a powerful tool to solve the weakly supervised classification in whole slide image (WSI) based pathology diagnosis.
Multiscale IoU: A Metric for Evaluation of Salient Object Detection with Fine Structures
General-purpose object-detection algorithms often dismiss the fine structure of detected objects.
Multi-functional microwave photonic radar system for simultaneous distance and velocity measurement and high-resolution microwave imaging
A photonic-assisted multi-functional radar system for simultaneous distance and velocity measurement and high-resolution microwave imaging is proposed and experimentally demonstrated by using a composite transmitted microwave signal of a single-chirped linearly frequency-modulated (LFM) signal and a single-tone microwave signal.
Towards Synthetic Multivariate Time Series Generation for Flare Forecasting
We utilize a flare forecasting benchmark dataset, named SWAN-SF, and design two verification methods to both quantitatively and qualitatively evaluate the similarity between the generated minority and the ground-truth samples.
Local Relation Learning for Face Forgery Detection
Specifically, we propose a Multi-scale Patch Similarity Module (MPSM), which measures the similarity between features of local regions and forms a robust and generalized similarity pattern.
Adversarial Inverse Reinforcement Learning for Mean Field Games
However, existing IRL methods for MFGs are powerless to reason about uncertainties in demonstrated behaviours of individual agents.
Multiple radio frequency measurement with an improved frequency resolution based on stimulated Brillouin scattering with a reduced gain bandwidth
The unknown RF signal is also SSB modulated on a carrier that has been modulated by a sweep signal, thus the unknown RF signal is converted to a sweep optical signal along with the sweep optical carrier.
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval
In this paper, we propose a CLIP4Clip model to transfer the knowledge of the CLIP model to video-language retrieval in an end-to-end manner.
Ranked #1 on
Text to Video Retrieval
on MSR-VTT
Achieving Domain Generalization in Underwater Object Detection by Domain Mixup and Contrastive Learning
Second, for the images with the same semantic content in different domains, their hidden features should be equivalent.
Topologically protected valley-dependent quantum photonic circuits
Topological photonics has been introduced as a powerful platform for integrated optics, since it can deal with robust light transport, and be further extended to the quantum world.
Quantum Physics Optics
The Post-impact Evolution of the X-ray Emitting Gas in SNR 1987A Viewed by XMM-Newton
In the last few years, the emission measure of the low-temperature plasma has been decreasing, indicating that the blast wave has left the main ER.
High Energy Astrophysical Phenomena
On the hard $γ$-ray spectrum of the potential PeVatron supernova remnant G106.3+2.7
The Tibet AS$\gamma$ experiment has measured $\gamma$-ray flux of supernova remnant G106. 3+2. 7 up to 100 TeV, suggesting it {being} potentially a "PeVatron".
High Energy Astrophysical Phenomena
Revealing a peculiar supernova remnant G106.3+2.7 as a petaelectronvolt proton accelerator with X-ray observations
Supernova remnants (SNRs) have long been considered as one of the most promising sources of Galactic cosmic rays.
High Energy Astrophysical Phenomena
LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT
Compressed sensing (CS) computed tomography has been proven to be important for several clinical applications, such as sparse-view computed tomography (CT), digital tomosynthesis and interior tomography.
Model Selection for Cross-Lingual Transfer
Transformers that are pre-trained on multilingual corpora, such as, mBERT and XLM-RoBERTa, have achieved impressive cross-lingual transfer capabilities.
Model Selection for Cross-Lingual Transfer using a Learned Scoring Function
In the zero-shot cross-lingual transfer setting, only English training data is assumed, and the fine-tuned model is evaluated on another target language.
Iterative Reconstruction for Low-Dose CT using Deep Gradient Priors of Generative Model
Dose reduction in computed tomography (CT) is essential for decreasing radiation risk in clinical applications.
FTN: Foreground-Guided Texture-Focused Person Re-Identification
Person re-identification (Re-ID) is a challenging task as persons are often in different backgrounds.
Remote sensing image fusion based on Bayesian GAN
Remote sensing image fusion technology (pan-sharpening) is an important means to improve the information capacity of remote sensing images.
Self-Organizing Map assisted Deep Autoencoding Gaussian Mixture Model for Intrusion Detection
In this paper, we propose a self-organizing map assisted deep autoencoding Gaussian mixture model (SOMDAGMM) supplemented with well-preserved input space topology for more accurate network intrusion detection.
Homotopic Gradients of Generative Density Priors for MR Image Reconstruction
Deep learning, particularly the generative model, has demonstrated tremendous potential to significantly speed up image reconstruction with reduced measurements recently.
Self-supervised Light Field View Synthesis Using Cycle Consistency
In order to enhance the angular resolution of light fields, view synthesis methods can be utilized to generate dense intermediate views from sparse light field input.
Fast and Accurate Optical Flow based Depth Map Estimation from Light Fields
Depth map estimation is a crucial task in computer vision, and new approaches have recently emerged taking advantage of light fields, as this new imaging modality captures much more information about the angular direction of light rays compared to common approaches based on stereoscopic images or multi-view.
A Study of Efficient Light Field Subsampling and Reconstruction Strategies
Limited angular resolution is one of the main obstacles for practical applications of light fields.
Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Images
Deep learning-based medical image registration and segmentation joint models utilize the complementarity (augmentation data or weakly supervised data from registration, region constraints from segmentation) to bring mutual improvement in complex scene and few-shot situation.
SMAP: A Joint Dimensionality Reduction Scheme for Secure Multi-Party Visualization
We build a prototype system based on our method, SMAP, to support the organization, computation, and exploration of secure joint embedding.
A Latent Mixture Model for Heterogeneous Causal Mechanisms in Mendelian Randomization
Existing MR methods usually assume most genetic variants are valid instrumental variables that identify a common causal effect.
Applications Methodology
Marginal loss and exclusion loss for partially supervised multi-organ segmentation
Annotating multiple organs in medical images is both costly and time-consuming; therefore, existing multi-organ datasets with labels are often low in sample size and mostly partially labeled, that is, a dataset has a few organs labeled but not all organs.
PoPE: A population-based approach to model spatial structure of astronomical systems
We present a novel population-based Bayesian inference approach to model the average and population variance of spatial distribution of a set of observables from ensemble analysis of low signal-to-noise ratio measurements.
Cosmology and Nongalactic Astrophysics Astrophysics of Galaxies Instrumentation and Methods for Astrophysics
Chemical abundances in Sgr A East: evidence for a type Iax supernova remnant
We report evidence that SNR Sgr A East in the Galactic center resulted from a pure turbulent deflagration of a Chandrasekhar-mass carbon-oxygen WD, an explosion mechanism used for type Iax SNe.
High Energy Astrophysical Phenomena
Progressively Unfreezing Perceptual GAN
Generative adversarial networks (GANs) are widely used in image generation tasks, yet the generated images are usually lack of texture details.
Noise-Sampling Cross Entropy Loss: Improving Disparity Regression Via Cost Volume Aware Regularizer
Recent end-to-end deep neural networks for disparity regression have achieved the state-of-the-art performance.
Learning Generalized Spoof Cues for Face Anti-spoofing
In this paper, we reformulate FAS in an anomaly detection perspective and propose a residual-learning framework to learn the discriminative live-spoof differences which are defined as the spoof cues.
An Empirical Study of Pre-trained Transformers for Arabic Information Extraction
Multilingual pre-trained Transformers, such as mBERT (Devlin et al., 2019) and XLM-RoBERTa (Conneau et al., 2020a), have been shown to enable the effective cross-lingual zero-shot transfer.
EB-dynaRE: Real-Time Adjustor for Brownian Movement with Examples of Predicting Stock Trends Based on a Novel Event-Based Supervised Learning Algorithm
The supervised learning algorithm used in this research, moreover, is original to this study and will have wider uses.
TPPO: A Novel Trajectory Predictor with Pseudo Oracle
A latent variable predictor is proposed to estimate latent variable distributions from observed and ground-truth trajectories.
A Novel Graph based Trajectory Predictor with Pseudo Oracle
Recent studies focus on modeling pedestrians' motion patterns with recurrent neural networks, capturing social interactions with pooling-based or graph-based methods, and handling future uncertainties by using random Gaussian noise as the latent variable.
Data Techniques For Online End-to-end Speech Recognition
Practitioners often need to build ASR systems for new use cases in a short amount of time, given limited in-domain data.
Semi-supervised ASR by End-to-end Self-training
While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Interpretable Click-Through Rate Prediction through Hierarchical Attention
For this problem, existing approaches, with shallow or deep architectures, have three major drawbacks.
Active Learning over DNN: Automated Engineering Design Optimization for Fluid Dynamics Based on Self-Simulated Dataset
Flood fill is used to define a boundary area function so that the optimal shape does not bypass the minimum area.
Interpreting LSTM Prediction on Solar Flare Eruption with Time-series Clustering
The dynamics of these parameters have a highly uniform trajectory for many events whose LSTM prediction scores for M/X class flares transition from very low to very high.
Solar Flare Intensity Prediction with Machine Learning Models
We develop a mixed Long Short Term Memory (LSTM) regression model to predict the maximum solar flare intensity within a 24-hour time window 0$\sim$24, 6$\sim$30, 12$\sim$36 and 24$\sim$48 hours ahead of time using 6, 12, 24 and 48 hours of data (predictors) for each Helioseismic and Magnetic Imager (HMI) Active Region Patch (HARP).
Solar and Stellar Astrophysics
"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.
Predicting solar flares with machine learning: investigating solar cycle dependence
A deep learning network, Long-Short Term Memory (LSTM) network, is used in this work to predict whether the maximum flare class an active region (AR) will produce in the next 24 hours is class $\Gamma$.
Solar and Stellar Astrophysics
Multi-Source Domain Adaptation and Semi-Supervised Domain Adaptation with Focus on Visual Domain Adaptation Challenge 2019
Semi-Supervised Domain Adaptation: For this task, we adopt a standard self-learning framework to construct a classifier based on the labeled source and target data, and generate the pseudo labels for unlabeled target data.
NGEMM: Optimizing GEMM for Deep Learning via Compiler-based Techniques
Various approaches have been developed by leveraging techniques such as vectorization and memory layout to improve the performance of integer GEMM.
EntEval: A Holistic Evaluation Benchmark for Entity Representations
Rich entity representations are useful for a wide class of problems involving entities.
Mocycle-GAN: Unpaired Video-to-Video Translation
Unsupervised image-to-image translation is the task of translating an image from one domain to another in the absence of any paired training examples and tends to be more applicable to practical applications.
An overlapping-free leaf segmentation method for plant point clouds
The proposed method can also facilitate the automatic traits estimation of each single leaf (such as the leaf area, length, and width), which has potential to become a highly effective tool for plant research and agricultural engineering.
PoMo: Generating Entity-Specific Post-Modifiers in Context
Given a sentence about a target entity, the task is to automatically generate a post-modifier phrase that provides contextually relevant information about the entity.
Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregation
The proposed algorithm is empirically on two datasets with different deep neural networks.
Student's t-Generative Adversarial Networks
We propose a new method referring to conditional GAN, which equipments the latent noise with mixture of Student's t-distribution with attention mechanism in addition to class information.
Structure Learning of Deep Networks via DNA Computing Algorithm
The indicates that: 1) Using DNA computing algorithm to learn deep architectures is feasible; 2) Local minima should not be a problem of deep networks; 3) We can use early stop to kill the models with the bad performance just after several runs of training.
Continual Learning of Context-dependent Processing in Neural Networks
Deep neural networks (DNNs) are powerful tools in learning sophisticated but fixed mapping rules between inputs and outputs, thereby limiting their application in more complex and dynamic situations in which the mapping rules are not kept the same but changing according to different contexts.
Ranked #5 on
Continual Learning
on ASC (19 tasks)
Deep Inferential Spatial-Temporal Network for Forecasting Air Pollution Concentrations
Air pollution poses a serious threat to human health as well as economic development around the world.
Denoising of 3-D Magnetic Resonance Images Using a Residual Encoder-Decoder Wasserstein Generative Adversarial Network
Structure-preserved denoising of 3D magnetic resonance imaging (MRI) images is a critical step in medical image analysis.
CartoonGAN: Generative Adversarial Networks for Photo Cartoonization
Two novel losses suitable for cartoonization are proposed: (1) a semantic content loss, which is formulated as a sparse regularization in the high-level feature maps of the VGG network to cope with substantial style variation between photos and cartoons, and (2) an edge-promoting adversarial loss for preserving clear edges.
Souper: A Synthesizing Superoptimizer
If we can automatically derive compiler optimizations, we might be able to sidestep some of the substantial engineering challenges involved in creating and maintaining a high-quality compiler.
Programming Languages
Learning to Rank Retargeted Images
Observing that it is challenging even for human subjects to give consistent scores for retargeting results of different source images, in this paper we propose a learning-based OQA method that predicts the ranking of a set of retargeted images with the same source image.
MomentsNet: a simple learning-free method for binary image recognition
In this paper, we propose a new simple and learning-free deep learning network named MomentsNet, whose convolution layer, nonlinear processing layer and pooling layer are constructed by Moments kernels, binary hashing and block-wise histogram, respectively.
Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)
Given the potential X-ray radiation risk to the patient, low-dose CT has attracted a considerable interest in the medical imaging field.
Denoising Hyperspectral Image with Non-i.i.d. Noise Structure
In real scenarios, however, the noise existed in a natural HSI is always with much more complicated non-i. i. d.
Blur Robust Optical Flow using Motion Channel
It is hard to estimate optical flow given a realworld video sequence with camera shake and other motion blur.
Low-rank Matrix Factorization under General Mixture Noise Distributions
Many computer vision problems can be posed as learning a low-dimensional subspace from high dimensional data.
Color Image Classification via Quaternion Principal Component Analysis Network
The Principal Component Analysis Network (PCANet), which is one of the recently proposed deep learning architectures, achieves the state-of-the-art classification accuracy in various databases.
Finding representative sets of optimizations for adaptive multiversioning applications
Iterative compilation is a widely adopted technique to optimize programs for different constraints such as performance, code size and power consumption in rapidly evolving hardware and software environments.
