Search Results for author:
Found 152 papers, 61 papers with code
Momentum Batch Normalization for Deep Learning with Small Batch Size
To make a deeper understanding of BN, in this work we prove that BN actually introduces a certain level of noise into the sample mean and variance during the training process, while the noise level depends only on the batch size.
Rethinking the Graph Polynomial Filter via Positive and Negative Coupling Analysis
Subsequently, PNCA is used to analyze the mainstream polynomial filters, and a novel simple basis that decouples the positive and negative activation and fully utilizes graph structure information is designed.
CRS-Diff: Controllable Generative Remote Sensing Foundation Model
The emergence of diffusion models has revolutionized the field of image generation, providing new methods for creating high-quality, high-resolution images across various applications.
TRG-Net: An Interpretable and Controllable Rain Generator
Our unpaired generation experiments demonstrate that the rain generated by the proposed rain generator is not only of higher quality, but also more effective for deraining and downstream tasks compared to current state-of-the-art rain generation methods.
Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud?
Current state-of-the-art (SOTA) 3D object detection methods often require a large amount of 3D bounding box annotations for training.
DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion
To effectively mine the complementary information and adapt to misalignment situations, we propose a Multispectral Deformable Cross-attention module to adaptively sample and aggregate multi-semantic level features of infrared and visible images for each object.
HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models
Specifically, the reduced image, which has a low spectral dimension, lies in the image field and can be inferred from our improved diffusion model where a new guidance function with total variation (TV) prior is designed to ensure that the reduced image can be well sampled.
Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling
This paper focuses on semi-supervised crowd counting, where only a small portion of the training data are labeled.
Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks
Neural networks demonstrate inherent vulnerability to small, non-random perturbations, emerging as adversarial attacks.
InfMAE: A Foundation Model in Infrared Modality
Finally, based on the fact that infrared images do not have a lot of details and texture information, we design an infrared decoder module, which further improves the performance of downstream tasks.
Gramformer: Learning Crowd Counting via Graph-Modulated Transformer
The graph is building upon the dissimilarities between patches, modulating the attention in an anti-similarity fashion.
Revisiting Nonlocal Self-Similarity from Continuous Representation
Extensive multi-dimensional data processing experiments on-meshgrid (e. g., image inpainting and image denoising) and off-meshgrid (e. g., climate data prediction and point cloud recovery) validate the versatility, effectiveness, and efficiency of our CRNL as compared with state-of-the-art methods.
Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restoration
In current deep unfolding methods, such a proximal network is generally designed as a CNN architecture, whose necessity has been proven by a recent theory.
Guided Image Restoration via Simultaneous Feature and Image Guided Fusion
Currently, joint image filtering-inspired deep learning-based methods represent the state-of-the-art for GIR tasks.
A New Learning Paradigm for Foundation Model-based Remote Sensing Change Detection
Change detection (CD) is a critical task to observe and analyze dynamic processes of land cover.
Building change detection for remote sensing images
Change Detection
+1
Provable Tensor Completion with Graph Information
For the model, we establish a rigorous mathematical representation of the dynamic graph, based on which we derive a new tensor-oriented graph smoothness regularization.
FRS-Nets: Fourier Parameterized Rotation and Scale Equivariant Networks for Retinal Vessel Segmentation
To embed more equivariance into CNNs and achieve the accuracy requirement for retinal vessel segmentation, we construct a novel convolution operator (FRS-Conv), which is Fourier parameterized and equivariant to rotation and scaling.
CA2: Class-Agnostic Adaptive Feature Adaptation for One-class Classification
We generalize the center-based method to unknown classes and optimize this objective based on the prior existing in the pre-trained network, i. e., pre-trained features that belong to the same class are adjacent.
Cross-Consistent Deep Unfolding Network for Adaptive All-In-One Video Restoration
To empower the framework for eliminating diverse degradations, we devise a Sequence-wise Adaptive Degradation Estimator (SADE) to estimate degradation features for the input corrupted video.
Neural Gradient Regularizer
NGR is applicable to various image types and different image processing tasks, functioning in a zero-shot learning fashion, making it a versatile and plug-and-play regularizer.
CBA: Improving Online Continual Learning via Continual Bias Adaptor
Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams.
A Low-rank Matching Attention based Cross-modal Feature Fusion Method for Conversational Emotion Recognition
By setting a matching weight and calculating attention scores between modal features row by row, LMAM contains fewer parameters than the self-attention method.
Unsupervised Hyperspectral Pansharpening via Low-rank Diffusion Model
To address these issues, in this work, we propose a low-rank diffusion model for hyperspectral pansharpening by simultaneously leveraging the power of the pre-trained deep diffusion model and better generalization ability of Bayesian methods.
DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning
Besides, meta-data-driven meta-loss objective combined with DAC-MR is capable of achieving better meta-level generalization.
PanFlowNet: A Flow-Based Deep Network for Pan-sharpening
The experimental results verify that the proposed PanFlowNet can generate various HRMS images given an LRMS image and a PAN image.
T-former: An Efficient Transformer for Image Inpainting
And based on this attention, a network called $T$-former is designed for image inpainting.
Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection
State-of-the-art 3D object detectors are usually trained on large-scale datasets with high-quality 3D annotations.
Random Weights Networks Work as Loss Prior Constraint for Image Restoration
In this paper, orthogonal to the existing data and model studies, we instead resort our efforts to investigate the potential of loss function in a new perspective and present our belief ``Random Weights Networks can Be Acted as Loss Prior Constraint for Image Restoration''.
Regularize implicit neural representation by itself
The smoothness of the Laplacian matrix is further integrated by parameterizing DE with a tiny INR.
DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion
To leverage strong generative priors and address challenges such as unstable training and lack of interpretability for GAN-based generative methods, we propose a novel fusion algorithm based on the denoising diffusion probabilistic model (DDPM).
Probability-based Global Cross-modal Upsampling for Pansharpening
Pansharpening is an essential preprocessing step for remote sensing image processing.
Interactive Segmentation as Gaussian Process Classification
Against this issue, in this paper, we propose to formulate the IS task as a Gaussian process (GP)-based pixel-wise binary classification model on each image.
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness
Recent research have made significant progress by adopting two insightful tensor priors, i. e., global low-rankness (L) and local smoothness (S) across different tensor modes, which are always encoded as a sum of two separate regularization terms into the recovery models.
Improve Noise Tolerance of Robust Loss via Noise-Awareness
To achieve setting such instance-dependent hyperparameters for robust loss, we propose a meta-learning method capable of adaptively learning a hyperparameter prediction function, called Noise-Aware-Robust-Loss-Adjuster (NARL-Adjuster).
Deep Diversity-Enhanced Feature Representation of Hyperspectral Images
In this paper, we study the problem of efficiently and effectively embedding the high-dimensional spatio-spectral information of hyperspectral (HS) images, guided by feature diversity.
Interactive Segmentation As Gaussion Process Classification
Against this issue, in this paper, we propose to formulate the IS task as a Gaussian process (GP)-based pixel-wise binary classification model on each image.
NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical Development Patterns of Preterm Infants
Deploying reliable deep learning techniques in interdisciplinary applications needs learned models to output accurate and (even more importantly) explainable predictions.
Dual Meta-Learning with Longitudinally Consistent Regularization for One-Shot Brain Tissue Segmentation Across the Human Lifespan
However, segmentation on longitudinal data is challenging due to dynamic brain changes across the lifespan.
S2S-WTV: Seismic Data Noise Attenuation Using Weighted Total Variation Regularized Self-Supervised Learning
In this work, we propose a self-supervised method that combines the capacities of deep denoiser and the generalization abilities of hand-crafted regularization for seismic data random noise attenuation.
Orientation-Shared Convolution Representation for CT Metal Artifact Learning
During X-ray computed tomography (CT) scanning, metallic implants carrying with patients often lead to adverse artifacts in the captured CT images and then impair the clinical treatment.
A Hyper-weight Network for Hyperspectral Image Denoising
Extensive experiments verify that the proposed HWnet can help improve the generalization ability of a weighted model to adapt to more complex noise, and can also strengthen the weighted model by transferring the knowledge from another weighted model.
Low-Rank Tensor Function Representation for Multi-Dimensional Data Recovery
To break this barrier, we propose a low-rank tensor function representation (LRTFR), which can continuously represent data beyond meshgrid with infinite resolution.
Fast Noise Removal in Hyperspectral Images via Representative Coefficient Total Variation
The model-based methods have good generalization ability, while the runtime cannot meet the fast processing requirements of the practical situations due to the large size of an HSI data $ \mathbf{X} \in \mathbb{R}^{MN\times B}$.
Deep Fourier Up-Sampling
Existing convolutional neural networks widely adopt spatial down-/up-sampling for multi-scale modeling.
KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution
Although current deep learning-based methods have gained promising performance in the blind single image super-resolution (SISR) task, most of them mainly focus on heuristically constructing diverse network architectures and put less emphasis on the explicit embedding of the physical generation mechanism between blur kernels and high-resolution (HR) images.
Imbalanced Semi-supervised Learning with Bias Adaptive Classifier
The core idea is to automatically assimilate the training bias caused by class imbalance via the bias adaptive classifier, which is composed of a novel bias attractor and the original linear classifier.
Adaptive Convolutional Dictionary Network for CT Metal Artifact Reduction
By unfolding every iterative substep of the proposed algorithm into a network module, we explicitly embed the prior structure into a deep network, \emph{i. e.,} a clear interpretability for the MAR task.
Decoupled-and-Coupled Networks: Self-Supervised Hyperspectral Image Super-Resolution with Subpixel Fusion
Enormous efforts have been recently made to super-resolve hyperspectral (HS) images with the aid of high spatial resolution multispectral (MS) images.
Hyperspectral Image Super-Resolution
Image Super-Resolution
+1
On the uncertainty principle of neural networks
Despite the successes in many fields, it is found that neural networks are difficult to be both accurate and robust, i. e., high accuracy networks are often vulnerable.
Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation
The state-of-the-art deep learning-based methods often simply concatenate the raw geometric attributes (i. e., coordinates and normal vectors) of mesh cells to train a single-stream network for automatic intra-oral scanner image segmentation.
Diagnosing Batch Normalization in Class Incremental Learning
Extensive researches have applied deep neural networks (DNNs) in class incremental learning (Class-IL).
Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustment
Besides, to avoid manually parameter tuning, we also propose a self-supervised fine-tuning strategy, which can always guarantee a promising performance.
CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning
Specifically, by seeing each training class as a separate learning task, our method aims to extract an explicit weighting function with sample loss and task/class feature as input, and sample weight as output, expecting to impose adaptively varying weighting schemes to different sample classes based on their own intrinsic bias characteristics.
Ranked #3 on
Image Classification
on WebVision-1000
Exact Decomposition of Joint Low Rankness and Local Smoothness Plus Sparse Matrices
It is known that the decomposition in low-rank and sparse matrices (\textbf{L+S} for short) can be achieved by several Robust PCA techniques.
SS3D: Sparsely-Supervised 3D Object Detection From Point Cloud
In the meantime, we design a reliable background mining module and a point cloud filling data augmentation strategy to generate the confident data for iteratively learning with reliable supervision.
HLRTF: Hierarchical Low-Rank Tensor Factorization for Inverse Problems in Multi-Dimensional Imaging
Inverse problems in multi-dimensional imaging, e. g., completion, denoising, and compressive sensing, are challenging owing to the big volume of the data and the inherent ill-posedness.
Relational Experience Replay: Continual Learning by Adaptively Tuning Task-wise Relationship
Continual learning is a promising machine learning paradigm to learn new tasks while retaining previously learned knowledge over streaming training data.
An Efficient and Accurate Rough Set for Feature Selection, Classification and Knowledge Representation
This paper present a strong data mining method based on rough set, which can realize feature selection, classification and knowledge representation at the same time.
InDuDoNet+: A Deep Unfolding Dual Domain Network for Metal Artifact Reduction in CT Images
To alleviate these issues, in the paper, we construct a novel deep unfolding dual domain network, termed InDuDoNet+, into which CT imaging process is finely embedded.
Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifiers
Existing methods commonly address hierarchical classification by decoupling it into a series of multi-class classification tasks.
Infrared Small-Dim Target Detection with Transformer under Complex Backgrounds
We adopt the self-attention mechanism of the transformer to learn the interaction information of image features in a larger range.
InDuDoNet: An Interpretable Dual Domain Network for CT Metal Artifact Reduction
For the task of metal artifact reduction (MAR), although deep learning (DL)-based methods have achieved promising performances, most of them suffer from two problems: 1) the CT imaging geometry constraint is not fully embedded into the network during training, leaving room for further performance improvement; 2) the model interpretability is lack of sufficient consideration.
Unsupervised Local Discrimination for Medical Images
To address this challenge, in this paper, we propose a general unsupervised representation learning framework, named local discrimination (LD), to learn local discriminative features for medical images by closely embedding semantically similar pixels and identifying regions of similar structures across different images.
Local Patch Network with Global Attention for Infrared Small Target Detection
A local patch network (LPNet) with global attention is proposed in this paper to detect small targets by jointly considering the global and local properties of infrared small target images.
Fourier Series Expansion Based Filter Parametrization for Equivariant Convolutions
It has been shown that equivariant convolution is very helpful for many types of computer vision tasks.
RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining
To handle such an ill-posed single image deraining task, in this paper, we specifically build a novel deep architecture, called rain convolutional dictionary network (RCDNet), which embeds the intrinsic priors of rain streaks and has clear interpretability.
Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks
Meta learning has attracted much attention recently in machine learning community.
Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel
To address the above issues, this paper proposes a model-based blind SISR method under the probabilistic framework, which elaborately models image degradation from the perspectives of noise and blur kernel.
Residual Moment Loss for Medical Image Segmentation
Location information is proven to benefit the deep learning models on capturing the manifold structure of target objects, and accordingly boosts the accuracy of medical image segmentation.
Instance-based Vision Transformer for Subtyping of Papillary Renal Cell Carcinoma in Histopathological Image
Histological subtype of papillary (p) renal cell carcinoma (RCC), type 1 vs. type 2, is an essential prognostic factor.
Nuclei Grading of Clear Cell Renal Cell Carcinoma in Histopathological Image by Composite High-Resolution Network
In this paper, we propose a Composite High-Resolution Network for ccRCC nuclei grading.
TSGCNet: Discriminative Geometric Feature Learning With Two-Stream Graph Convolutional Network for 3D Dental Model Segmentation
State-of-the-art methods directly concatenate the raw attributes of 3D inputs, namely coordinates and normal vectors of mesh cells, to train a single-stream network for fully-automated tooth segmentation.
Learning an Explicit Weighting Scheme for Adapting Complex HSI Noise
A general approach for handling hyperspectral image (HSI) denoising issue is to impose weights on different HSI pixels to suppress negative influence brought by noisy elements.
Effective Snapshot Compressive-Spectral Imaging via Deep Denoising and Total Variation Priors
Specifically, we propose an optimization objective to utilize these two priors.
A Deep Variational Bayesian Framework for Blind Image Deblurring
Under this framework, the posterior of the latent clean image and blur kernel can be jointly estimated in an amortized inference fashion with DNNs, and the involved inference DNNs can be trained by fully considering the physical blur model, together with the supervision of data driven priors for the clean image and blur kernel, which is naturally led to by the evidence lower bound objective.
EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network
Recently, it has been demonstrated that the performance of a deep convolutional neural network can be effectively improved by embedding an attention module into it.
Semi-Supervised Video Deraining with Dynamical Rain Generator
Firstly, most of them do not sufficiently model the characteristics of rain layers of rainy videos.
Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond
Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community.
A self-explanatory method for the black problem on discrimination part of CNN
However, it is hard for the interpretable models to approximate the discrimination part because of the tradeoff problem between interpretability performance and generalization performance of the discrimination part.
TSGCNet: Discriminative Geometric Feature Learning with Two-Stream GraphConvolutional Network for 3D Dental Model Segmentation
State-of-the-art methods directly concatenate the raw attributes of 3D inputs, namely coordinates and normal vectors of mesh cells, to train a single-stream network for fully-automated tooth segmentation.
Unsupervised Learning of Local Discriminative Representation for Medical Images
However, the commonly applied supervised representation learning methods require a large amount of annotated data, and unsupervised discriminative representation learning distinguishes different images by learning a global feature, both of which are not suitable for localized medical image analysis tasks.
Select-ProtoNet: Learning to Select for Few-Shot Disease Subtype Prediction
Current machine learning has made great progress on computer vision and many other fields attributed to the large amount of high-quality training samples, while it does not work very well on genomic data analysis, since they are notoriously known as small data.
Deep Variational Network Toward Blind Image Restoration
In this proposed model, a pixel-wise non-i. i. d.
Meta Feature Modulator for Long-tailed Recognition
We further design a modulator network to guide the generation of the modulation parameters, and such a meta-learner can be readily adapted to train the classification network on other long-tailed datasets.
From Rain Generation to Rain Removal
For the single image rain removal (SIRR) task, the performance of deep learning (DL)-based methods is mainly affected by the designed deraining models and training datasets.
Learning to Purify Noisy Labels via Meta Soft Label Corrector
By viewing the label correction procedure as a meta-process and using a meta-learner to automatically correct labels, we could adaptively obtain rectified soft labels iteratively according to current training problems without manually preset hyper-parameters.
MLR-SNet: Transferable LR Schedules for Heterogeneous Tasks
Meanwhile, it always needs to search proper LR schedules from scratch for new tasks, which, however, are often largely different with task variations, like data modalities, network architectures, or training data capacities.
Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation
Specifically, we approximate the joint distribution with two different factorized forms, which can be formulated as a denoiser mapping the noisy image to the clean one and a generator mapping the clean image to the noisy one.
Ranked #2 on
Noise Estimation
on SIDD
Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution
The recent advancement of deep learning techniques has made great progress on hyperspectral image super-resolution (HSI-SR).
Meta Transition Adaptation for Robust Deep Learning with Noisy Labels
To discover intrinsic inter-class transition probabilities underlying data, learning with noise transition has become an important approach for robust deep learning on corrupted labels.
Structural Residual Learning for Single Image Rain Removal
Such a structural residual setting guarantees the rain layer extracted by the network finely comply with the prior knowledge of general rain streaks, and thus regulates sound rain shapes capable of being well extracted from rainy images in both training and predicting stages.
A Model-driven Deep Neural Network for Single Image Rain Removal
Specifically, based on the convolutional dictionary learning mechanism for representing rain, we propose a novel single image deraining model and utilize the proximal gradient descent technique to design an iterative algorithm only containing simple operators for solving the model.
Ball k-means
The assigned cluster of the points in the stable area is not changed in the current iteration while the points in the annulus area will be adjusted within a few neighbor clusters in the current iteration.
LT-Net: Label Transfer by Learning Reversible Voxel-wise Correspondence for One-shot Medical Image Segmentation
We introduce a one-shot segmentation method to alleviate the burden of manual annotation for medical images.
Learning Adaptive Loss for Robust Learning with Noisy Labels
Four kinds of SOTA robust loss functions are attempted to be integrated into our algorithm, and comprehensive experiments substantiate the general availability and effectiveness of the proposed method in both its accuracy and generalization performance, as compared with conventional hyperparameter tuning strategy, even with carefully tuned hyperparameters.
A Survey on Rain Removal from Video and Single Image
The investigations on rain removal from video or a single image has thus been attracting much research attention in the field of computer vision and pattern recognition, and various methods have been proposed against this task in the recent years.
Video Rain/Snow Removal by Transformed Online Multiscale Convolutional Sparse Coding
Furthermore, a transformation operator imposed on the background scenes is further embedded into the proposed model, which finely conveys the dynamic background transformations, such as rotations, scalings and distortions, inevitably existed in a real video sequence.
Variational Denoising Network: Toward Blind Noise Modeling and Removal
On one hand, as other data-driven deep learning methods, our method, namely variational denoising network (VDN), can perform denoising efficiently due to its explicit form of posterior expression.
Ranked #10 on
Image Denoising
on DND
Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting
Current deep neural networks (DNNs) can easily overfit to biased training data with corrupted labels or class imbalance.
Ranked #24 on
Image Classification
on Clothing1M
(using extra training data)
Progressive Image Deraining Networks: A Better and Simpler Baseline
To handle this issue, this paper provides a better and simpler baseline deraining network by considering network architecture, input and output, and loss functions.
Ranked #1 on
Single Image Deraining
on Rain1400
Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net
In this paper, we propose a model-based deep learning approach for merging an HrMS and LrHS images to generate a high-resolution hyperspectral (HrHS) image.
Model Inconsistent but Correlated Noise: Multi-view Subspace Learning with Regularized Mixture of Gaussians
Different from single view case, MSL should take both common and specific knowledge among different views into consideration.
Enhanced 3DTV Regularization and Its Applications on Hyper-spectral Image Denoising and Compressed Sensing
The 3-D total variation (3DTV) is a powerful regularization term, which encodes the local smoothness prior structure underlying a hyper-spectral image (HSI), for general HSI processing tasks.
Discovering Influential Factors in Variational Autoencoder
In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks.
Small Sample Learning in Big Data Era
This category mainly focuses on learning with insufficient samples, and can also be called small data learning in some literatures.
Unsupervised/Semi-supervised Deep Learning for Low-dose CT Enhancement
To address this issue, we propose an unsupervised DL method for LdCT enhancement that incorporates unlabeled LdCT sinograms directly into the network training.
Semi-supervised Transfer Learning for Image Rain Removal
However, previous deep learning methods need to pre-collect a large set of image pairs with/without synthesized rain for training, which tends to make the neural network be biased toward learning the specific patterns of the synthesized rain, while be less able to generalize to real test samples whose rain types differ from those in the training data.
Ranked #8 on
Single Image Deraining
on Test100
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.
Discriminative Feature Learning with Foreground Attention for Person Re-Identification
Specifically, a novel foreground attentive subnetwork is designed to drive the network's attention, in which a decoder network is used to reconstruct the binary mask by using a novel local regression loss function, and an encoder network is regularized by the decoder network to focus its attention on the foreground persons.
Video Rain Streak Removal by Multiscale Convolutional Sparse Coding
Based on such understanding, we specifically formulate both characteristics into a multiscale convolutional sparse coding (MS-CSC) model for the video rain streak removal task.
Understanding Self-Paced Learning under Concave Conjugacy Theory
By simulating the easy-to-hard learning manners of humans/animals, the learning regimes called curriculum learning~(CL) and self-paced learning~(SPL) have been recently investigated and invoked broad interests.
PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalities
As a result, using partial data channels to build a full representation of multi-modalities is clearly desired.
Preliminary theoretical troubleshooting in Variational Autoencoder
This paper tries to preliminarily address VAE's intrinsic dimension, real factor, disentanglement and indicator issues theoretically in the idealistic situation and implementation issue practically through noise modeling perspective in the realistic case.
DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation
DecideNet starts with estimating the crowd density by generating detection and regression based density maps separately.
Ranked #10 on
Crowd Counting
on WorldExpo’10
Deep Self-Paced Learning for Person Re-Identification
In this paper, we propose a novel deep self-paced learning (DSPL) algorithm to alleviate this problem, in which we apply a self-paced constraint and symmetric regularization to help the relative distance metric training the deep neural network, so as to learn the stable and discriminative features for person Re-ID.
Joint Convolutional Analysis and Synthesis Sparse Representation for Single Image Layer Separation
To exploit the complementary representation mechanisms of ASR and SSR, we integrate the two models and propose a joint convolutional analysis and synthesis (JCAS) sparse representation model.
Tensor RPCA by Bayesian CP Factorization With Complex Noise
In this paper, we propose a tensor RPCA model based on CP decomposition and model data noise by Mixture of Gaussians (MoG).
Should We Encode Rain Streaks in Video as Deterministic or Stochastic?
Videos taken in the wild sometimes contain unexpected rain streaks, which brings difficulty in subsequent video processing tasks.
Self-Paced Co-training
During co-training process, labels of unlabeled instances in the training pool are very likely to be false especially in the initial training rounds, while the standard co-training algorithm utilizes a “draw without replacement” manner and does not remove these false labeled instances from training.
Hyperspectral Image Restoration via Total Variation Regularized Low-rank Tensor Decomposition
In this paper, we present a novel tensor-based HSI restoration approach by fully identifying the intrinsic structures of the clean HSI part and the mixed noise part respectively.
SPFTN: A Self-Paced Fine-Tuning Network for Segmenting Objects in Weakly Labelled Videos
Object segmentation in weakly labelled videos is an interesting yet challenging task, which aims at learning to perform category-specific video object segmentation by only using video-level tags.
Few-Example Object Detection with Model Communication
Experiments on PASCAL VOC'07, MS COCO'14, and ILSVRC'13 indicate that by using as few as three or four samples selected for each category, our method produces very competitive results when compared to the state-of-the-art weakly-supervised approaches using a large number of image-level labels.
Ranked #1 on
Weakly Supervised Object Detection
on MS COCO
SPLBoost: An Improved Robust Boosting Algorithm Based on Self-paced Learning
Specifically, the underlying loss being minimized by the traditional AdaBoost is the exponential loss, which is proved to be very sensitive to random noise/outliers.
Robust Online Matrix Factorization for Dynamic Background Subtraction
We propose an effective online background subtraction method, which can be robustly applied to practical videos that have variations in both foreground and background.
A General Model for Robust Tensor Factorization with Unknown Noise
We provide two versions of the algorithm with different tensor factorization operations, i. e., CP factorization and Tucker factorization.
Hyperspectral Image Classification with Markov Random Fields and a Convolutional Neural Network
This paper presents a new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework.
Ranked #13 on
Hyperspectral Image Classification
on Indian Pines
(Overall Accuracy metric, using extra
training data)
On Convergence Property of Implicit Self-paced Objective
Recently, it has been proved that the SPL regime has a close relationship to a implicit self-paced objective function.
Bridging Saliency Detection to Weakly Supervised Object Detection Based on Self-paced Curriculum Learning
Weakly-supervised object detection (WOD) is a challenging problems in computer vision.
Ranked #34 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
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.
Active Self-Paced Learning for Cost-Effective and Progressive Face Identification
By naturally combining two recently rising techniques: active learning (AL) and self-paced learning (SPL), our framework is capable of automatically annotating new instances and incorporating them into training under weak expert re-certification.
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance.
Exploiting Multi-modal Curriculum in Noisy Web Data for Large-scale Concept Learning
Learning video concept detectors automatically from the big but noisy web data with no additional manual annotations is a novel but challenging area in the multimedia and the machine learning community.
Strategies for Searching Video Content with Text Queries or Video Examples
The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search.
Multispectral Images Denoising by Intrinsic Tensor Sparsity Regularization
Multispectral images (MSI) can help deliver more faithful representation for real scenes than the traditional image system, and enhance the performance of many computer vision tasks.
Robust Tensor Factorization With Unknown Noise
However, real data are often corrupted by noise with an unknown distribution.
The Solution Path Algorithm for Identity-Aware Multi-Object Tracking
The tracker is formulated as a quadratic optimization problem with L0 norm constraints, which we propose to solve with the solution path algorithm.
A novel learning-based frame pooling method for Event Detection
Detecting complex events in a large video collection crawled from video websites is a challenging task.
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.
Convolutional Sparse Coding for Image Super-Resolution
Sparse coding (SC) plays an important role in versatile computer vision applications such as image super-resolution (SR).
A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection
As an interesting and emerging topic, co-saliency detection aims at simultaneously extracting common salient objects in a group of images.
A Novel Sparsity Measure for Tensor Recovery
In this paper, we propose a new sparsity regularizer for measuring the low-rank structure underneath a tensor.
What Objective Does Self-paced Learning Indeed Optimize?
Self-paced learning (SPL) is a recently raised methodology designed through simulating the learning principle of humans/animals.
Detail-preserving and Content-aware Variational Multi-view Stereo Reconstruction
It is much more promising in suppressing noise while preserving sharp features than conventional isotropic mesh smoothing.
Total Variation Regularized Tensor RPCA for Background Subtraction from Compressive Measurements
In this paper, we propose a novel tensor-based robust PCA (TenRPCA) approach for BSCM by decomposing video frames into backgrounds with spatial-temporal correlations and foregrounds with spatio-temporal continuity in a tensor framework.
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.
Self-Paced Learning with Diversity
Self-paced learning (SPL) is a recently proposed learning regime inspired by the learning process of humans and animals that gradually incorporates easy to more complex samples into training.
Density-Based Region Search with Arbitrary Shape for Object Localization
Typically, the region search methods project the score of a classifier into an image plane, and then search the region with the maximal score.
Transitive Distance Clustering with K-Means Duality
We propose a very intuitive and simple approximation for the conventional spectral clustering methods.
Decomposable Nonlocal Tensor Dictionary Learning for Multispectral Image Denoising
As compared to the conventional RGB or gray-scale images, multispectral images (MSI) can deliver more faithful representation for real scenes, and enhance the performance of many computer vision tasks.
On the Optimal Solution of Weighted Nuclear Norm Minimization
Nevertheless, so far the global optimal solution of WNNM problem is not completely solved yet due to its non-convexity in general cases.
FastMMD: Ensemble of Circular Discrepancy for Efficient Two-Sample Test
Taking advantage of sampling of Fourier transform, FastMMD decreases the time complexity for MMD calculation from $O(N^2 d)$ to $O(L N d)$, where $N$ and $d$ are the size and dimension of the sample set, respectively.
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.
