Search Results for author:
Found 78 papers, 27 papers with code
Perceptive self-supervised learning network for noisy image watermark removal
Specifically, mentioned paired watermark images are obtained in a self supervised way, and paired noisy images (i. e., noisy and reference images) are obtained in a supervised way.
CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay
Our method iterates between 1) program sampling and hindsight relabeling, and 2) learning from prioritized experience replay.
Towards Efficient Hyperdimensional Computing Using Photonics
Over the past few years, silicon photonics-based computing has emerged as a promising alternative to CMOS-based computing for Deep Neural Networks (DNN).
Efficient Model Adaptation for Continual Learning at the Edge
This paper presents the Encoder-Adaptor-Reconfigurator (EAR) framework for efficient continual learning under domain shifts.
Text Generation with Speech Synthesis for ASR Data Augmentation
In this work, we explore text augmentation for ASR using large-scale pre-trained neural networks, and systematically compare those to traditional text augmentation methods.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Deep adaptive hiding network for image hiding using attentive frequency extraction and gradual depth extraction
Image hiding secures information security in multimedia communication.
Multi-adversarial Faster-RCNN with Paradigm Teacher for Unrestricted Object Detection
Our proposed MAF has two distinct contributions: (1) The Hierarchical Domain Feature Alignment (HDFA) module is introduced to minimize the image-level domain disparity, where Scale Reduction Module (SRM) reduces the feature map size without information loss and increases the training efficiency.
Time-Efficient Reward Learning via Visually Assisted Cluster Ranking
One of the most successful paradigms for reward learning uses human feedback in the form of comparisons.
Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities
Later, we use our optimal tokenization strategy to train multiple embedding and output model to further improve our result.
A heterogeneous group CNN for image super-resolution
To prevent loss of original information, a multi-level enhancement mechanism guides a CNN to achieve a symmetric architecture for promoting expressive ability of HGSRCNN.
Multi-stage image denoising with the wavelet transform
In this paper, we propose a multi-stage image denoising CNN with the wavelet transform (MWDCNN) via three stages, i. e., a dynamic convolutional block (DCB), two cascaded wavelet transform and enhancement blocks (WEBs) and a residual block (RB).
Learning ASR pathways: A sparse multilingual ASR model
Neural network pruning compresses automatic speech recognition (ASR) models effectively.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Learning with Local Gradients at the Edge
To enable learning on edge devices with fast convergence and low memory, we present a novel backpropagation-free optimization algorithm dubbed Target Projection Stochastic Gradient Descent (tpSGD).
Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification
Based on our constructed dataset, we prove that with the increase of frames in a tracklet, the performance does meet more enhancement, demonstrating the significance of video-to-video matching in RGB-IR person Re-ID.
Real-time Hyper-Dimensional Reconfiguration at the Edge using Hardware Accelerators
In this paper we present Hyper-Dimensional Reconfigurable Analytics at the Tactical Edge (HyDRATE) using low-SWaP embedded hardware that can perform real-time reconfiguration at the edge leveraging non-MAC (free of floating-point MultiplyACcumulate operations) deep neural nets (DNN) combined with hyperdimensional (HD) computing accelerators.
Saccade Mechanisms for Image Classification, Object Detection and Tracking
We examine how the saccade mechanism from biological vision can be used to make deep neural networks more efficient for classification and object detection problems.
Image Super-resolution with An Enhanced Group Convolutional Neural Network
In this paper, we present an enhanced super-resolution group CNN (ESRGCNN) with a shallow architecture by fully fusing deep and wide channel features to extract more accurate low-frequency information in terms of correlations of different channels in single image super-resolution (SISR).
HIPA: Hierarchical Patch Transformer for Single Image Super Resolution
Transformer-based architectures start to emerge in single image super resolution (SISR) and have achieved promising performance.
Pseudocylindrical Convolutions for Learned Omnidirectional Image Compression
We first describe parametric pseudocylindrical representation as a generalization of common pseudocylindrical map projections.
Pedestrian Detection by Exemplar-Guided Contrastive Learning
Instead of learning each of these diverse pedestrian appearance features individually as most existing methods do, we propose to perform contrastive learning to guide the feature learning in such a way that the semantic distance between pedestrians with different appearances in the learned feature space is minimized to eliminate the appearance diversities, whilst the distance between pedestrians and background is maximized.
Ranked #1 on
Pedestrian Detection
on TJU-Ped-campus
Deep multi-modal aggregation network for MR image reconstruction with auxiliary modality
Magnetic resonance (MR) imaging produces detailed images of organs and tissues with better contrast, but it suffers from a long acquisition time, which makes the image quality vulnerable to say motion artifacts.
Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain
Existing methods for speech separation either transform the speech signals into frequency domain to perform separation or seek to learn a separable embedding space by constructing a latent domain based on convolutional filters.
Ranked #7 on
Speech Separation
on WHAMR!
BPFNet: A Unified Framework for Bimodal Palmprint Alignment and Fusion
Bimodal palmprint recognition leverages palmprint and palm vein images simultaneously, which achieves high accuracy by multi-model information fusion and has strong anti-falsification property.
Generative Memory-Guided Semantic Reasoning Model for Image Inpainting
Most existing methods for image inpainting focus on learning the intra-image priors from the known regions of the current input image to infer the content of the corrupted regions in the same image.
On lattice-free boosted MMI training of HMM and CTC-based full-context ASR models
Hybrid automatic speech recognition (ASR) models are typically sequentially trained with CTC or LF-MMI criteria.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Dual-Stream Reciprocal Disentanglement Learning for Domain Adaptation Person Re-Identification
Since human-labeled samples are free for the target set, unsupervised person re-identification (Re-ID) has attracted much attention in recent years, by additionally exploiting the source set.
Asymmetric CNN for image super-resolution
In this paper, we propose an asymmetric CNN (ACNet) comprising an asymmetric block (AB), a memory enhancement block (MEB) and a high-frequency feature enhancement block (HFFEB) for image super-resolution.
Touchless Palmprint Recognition based on 3D Gabor Template and Block Feature Refinement
To our best knowledge, it is the largest contactless palmprint image benchmark ever collected with regard to the number of individuals and palms.
Deep-Masking Generative Network: A Unified Framework for Background Restoration from Superimposed Images
In this work we present the Deep-Masking Generative Network (DMGN), which is a unified framework for background restoration from the superimposed images and is able to cope with different types of noise.
Designing and Training of A Dual CNN for Image Denoising
The enhancement block gathers and fuses the global and local features to provide complementary information for the latter network.
Embedding-based Retrieval in Facebook Search
In this paper, we discuss the techniques for applying EBR to a Facebook Search system.
Learning Context-Based Non-local Entropy Modeling for Image Compression
To address this issue, we propose a non-local operation for context modeling by employing the global similarity within the context.
Biometrics Recognition Using Deep Learning: A Survey
Deep learning-based models have been very successful in achieving state-of-the-art results in many of the computer vision, speech recognition, and natural language processing tasks in the last few years.
Bit Efficient Quantization for Deep Neural Networks
Quantization for deep neural networks have afforded models for edge devices that use less on-board memory and enable efficient low-power inference.
Non-negative Sparse and Collaborative Representation for Pattern Classification
In this paper, we propose a novel Non-negative Sparse and Collaborative Representation (NSCR) for pattern classification.
Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression
For the former, we directly apply a CCN to the binarized representation of an image to compute the Bernoulli distribution of each code for entropy estimation.
Remove Cosine Window from Correlation Filter-based Visual Trackers: When and How
Therefore, we in this paper investigate the feasibility to remove cosine window from CF trackers with spatial regularization.
Learning Content-Weighted Deep Image Compression
Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance.
Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation
The merits of the proposed MCTL are four-fold: 1) the concept of manifold criterion (MC) is first proposed as a measure validating the distribution matching across domains, and domain adaptation is achieved if the MC is satisfied; 2) the proposed MC can well guide the generation of the intermediate domain sharing similar distribution with the target domain, by minimizing the local domain discrepancy; 3) a global generative discrepancy metric (GGDM) is presented, such that both the global and local discrepancy can be effectively and positively reduced; 4) a simplified version of MCTL called MCTL-S is presented under a perfect domain generation assumption for more generic learning scenario.
Scaled Simplex Representation for Subspace Clustering
However, the negative entries in the coefficient matrix are forced to be positive when constructing the affinity matrix via exponentiation, absolute symmetrization, or squaring operations.
A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising
Most of existing image denoising methods assume the corrupted noise to be additive white Gaussian noise (AWGN).
Ranked #3 on
Denoising
on Darmstadt Noise Dataset
Sparse, Collaborative, or Nonnegative Representation: Which Helps Pattern Classification?
The use of sparse representation (SR) and collaborative representation (CR) for pattern classification has been widely studied in tasks such as face recognition and object categorization.
A Hybrid l1-l0 Layer Decomposition Model for Tone Mapping
State-of-the-art tone mapping algorithms mostly decompose an image into a base layer and a detail layer, and process them accordingly.
Simultaneous Fidelity and Regularization Learning for Image Restoration
For blind deconvolution, as estimation error of blur kernel is usually introduced, the subsequent non-blind deconvolution process does not restore the latent image well.
Real-world Noisy Image Denoising: A New Benchmark
In order to promote the study on this problem while implementing the concurrent real-world image denoising datasets, we construct a new benchmark dataset which contains comprehensive real-world noisy images of different natural scenes.
Dual Asymmetric Deep Hashing Learning
The deep hash functions are then learned through two networks by minimizing the gap between the learned features and discrete codes.
Enlarging Context with Low Cost: Efficient Arithmetic Coding with Trimmed Convolution
One key issue of arithmetic encoding method is to predict the probability of the current coding symbol from its context, i. e., the preceding encoded symbols, which usually can be executed by building a look-up table (LUT).
Integrating Boundary and Center Correlation Filters for Visual Tracking with Aspect Ratio Variation
The aspect ratio variation frequently appears in visual tracking and has a severe influence on performance.
Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising
Most of the existing denoising algorithms are developed for grayscale images, while it is not a trivial work to extend them for color image denoising because the noise statistics in R, G, B channels can be very different for real noisy images.
Ranked #5 on
Denoising
on Darmstadt Noise Dataset
External Prior Guided Internal Prior Learning for Real-World Noisy Image Denoising
We propose to exploit the information in both external data and the given noisy image, and develop an external prior guided internal prior learning method for real-world noisy image denoising.
Learning Convolutional Networks for Content-weighted Image Compression
Therefore, the encoder, decoder, binarizer and importance map can be jointly optimized in an end-to-end manner by using a subset of the ImageNet database.
GPU Activity Prediction using Representation Learning
GPU activity prediction is an important and complex problem.
Low Precision Neural Networks using Subband Decomposition
In this paper, we present a unique approach using lower precision weights for more efficient and faster training phase.
Deep Identity-aware Transfer of Facial Attributes
In general, our model consists of a mask network and an attribute transform network which work in synergy to generate a photo-realistic facial image with the reference attribute.
Ranked #2 on
Image-to-Image Translation
on RaFD
Convolutional Network for Attribute-driven and Identity-preserving Human Face Generation
Here we address this problem from the view of optimization, and suggest an optimization model to generate human face with the given attributes while keeping the identity of the reference image.
Joint Learning of Single-Image and Cross-Image Representations for Person Re-Identification
Person re-identification has been usually solved as either the matching of single-image representation (SIR) or the classification of cross-image representation (CIR).
Multi-modal Fusion for Diabetes Mellitus and Impaired Glucose Regulation Detection
has proved that tongue, face and sublingual diagnosis as a noninvasive method is a reasonable way for disease detection.
Quadratic Projection Based Feature Extraction with Its Application to Biometric Recognition
This paper presents a novel quadratic projection based feature extraction framework, where a set of quadratic matrices is learned to distinguish each class from all other classes.
Learning Domain-Invariant Subspace using Domain Features and Independence Maximization
In this paper, we focus on the problem of instrumental variation and time-varying drift in the field of sensors and measurement, which can be viewed as discrete and continuous distributional change in the feature space.
A survey of sparse representation: algorithms and applications
The main purpose of this article is to provide a comprehensive study and an updated review on sparse representation and to supply a guidance for researchers.
Robust Scene Text Recognition Using Sparse Coding based Features
For character detection, we use the HSC features instead of using the Histograms of Oriented Gradients (HOG) features.
Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising
PGs are extracted from training images by putting nonlocal similar patches into groups, and a PG based Gaussian Mixture Model (PG-GMM) learning algorithm is developed to learn the NSS prior.
SVM and ELM: Who Wins? Object Recognition with Deep Convolutional Features from ImageNet
In this report, we have discussed the nearest neighbor, support vector machines and extreme learning machines for image classification under deep convolutional activation feature representation.
Domain Adaptation Extreme Learning Machines for Drift Compensation in E-nose Systems
This paper proposes a unified framework, referred to as Domain Adaptation Extreme Learning Machine (DAELM), which learns a robust classifier by leveraging a limited number of labeled data from target domain for drift compensation as well as gases recognition in E-nose systems, without loss of the computational efficiency and learning ability of traditional ELM.
Visual Understanding via Multi-Feature Shared Learning with Global Consistency
This paper studies visual understanding via a newly proposed l_2-norm based multi-feature shared learning framework, which can simultaneously learn a global label matrix and multiple sub-classifiers with the labeled multi-feature data.
Evolutionary Cost-sensitive Extreme Learning Machine
Conventional extreme learning machines solve a Moore-Penrose generalized inverse of hidden layer activated matrix and analytically determine the output weights to achieve generalized performance, by assuming the same loss from different types of misclassification.
Robust Visual Knowledge Transfer via EDA
It allows us to learn a category transformation and an ELM classifier with random projection by minimizing the l_(2, 1)-norm of the network output weights and the learning error simultaneously.
Iterated Support Vector Machines for Distance Metric Learning
Distance metric learning aims to learn from the given training data a valid distance metric, with which the similarity between data samples can be more effectively evaluated for classification.
Fast Tracking via Spatio-Temporal Context Learning
In this paper, we present a simple yet fast and robust algorithm which exploits the spatio-temporal context for visual tracking.
A Kernel Classification Framework for Metric Learning
Learning a distance metric from the given training samples plays a crucial role in many machine learning tasks, and various models and optimization algorithms have been proposed in the past decade.
Image Set based Collaborative Representation for Face Recognition
One key issue of ISFR is how to effectively and efficiently represent the query face image set by using the gallery face image sets.
Texture Enhanced Image Denoising via Gradient Histogram Preservation
Image denoising is a classical yet fundamental problem in low level vision, as well as an ideal test bed to evaluate various statistical image modeling methods.
A Local Active Contour Model for Image Segmentation with Intensity Inhomogeneity
The means of the Gaussian distributions in the transformed domain can be adaptively estimated by multiplying a bias field with the original signal within the window.
Collaborative Representation based Classification for Face Recognition
It is widely believed that the l1- norm sparsity constraint on coding coefficients plays a key role in the success of SRC, while its use of all training samples to collaboratively represent the query sample is rather ignored.
Regularized Robust Coding for Face Recognition
Recently the sparse representation based classification (SRC) has been proposed for robust face recognition (FR).
FSIM: A Feature Similarity Index for Image Quality Assessment
Image quality assessment (IQA) aims to use computational models to measure the image quality consistently with subjective evaluations.
Ranked #2 on
Image Quality Assessment
on MSU FR VQA Database
Essence of kernel Fisher discriminant: KPCA plus LDA
In this paper, the method of kernel Fisher discriminant (KFD) is analyzed and its nature is revealed, i. e., KFD is equivalent to kernel principal component analysis (KPCA) plus Fisher linear discriminant analysis (LDA).
