Search Results for author:
Found 134 papers, 31 papers with code
Lesion-Aware Contrastive Representation Learning for Histopathology Whole Slide Images Analysis
In this paper, we proposed a novel contrastive representation learning framework named Lesion-Aware Contrastive Learning (LACL) for histopathology whole slide image analysis.
Kernel Attention Transformer (KAT) for Histopathology Whole Slide Image Classification
Transformer has been widely used in histopathology whole slide image (WSI) classification for the purpose of tumor grading, prognosis analysis, etc.
A Self-Guided Framework for Radiology Report Generation
Moreover, SGF successfully improves the accuracy and length of medical report generation by incorporating a similarity comparison mechanism that imitates the process of human self-improvement through compar-ative practice.
Design of optical voltage sensor based on electric field regulation and rotating isomerism electrode
This technology could shift the measured signal frequency band from near 50 Hz moved to several kilometer Hz, so as to make the output signal avoid the interference from low-frequency temperature drift, stress birefringence and vibration, leading to higher stability and reliability.
Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles
We introduce a new method, GSConv, to lighten the model but maintain the accuracy.
Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives
Transformer, the latest technological advance of deep learning, has gained prevalence in natural language processing or computer vision.
CompleteDT: Point Cloud Completion with Dense Augment Inference Transformers
Point cloud completion task aims to predict the missing part of incomplete point clouds and generate complete point clouds with details.
Providing Location Information at Edge Networks: A Federated Learning-Based Approach
Recently, the development of mobile edge computing has enabled exhilarating edge artificial intelligence (AI) with fast response and low communication cost.
A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model
Under the short-run non-mixing MCMC scenario, the estimation of the energy-based model is shown to follow the perturbation of maximum likelihood, and the short-run Langevin flow and the normalizing flow form a two-flow generator that we call CoopFlow.
CoDo: Contrastive Learning with Downstream Background Invariance for Detection
To bridge the performance gap, we propose a novel object-level self-supervised learning method, called Contrastive learning with Downstream background invariance (CoDo).
Optical Remote Sensing Image Understanding with Weak Supervision: Concepts, Methods, and Perspectives
Therefore, remote sensing image understanding often faces the problems of incomplete, inexact, and inaccurate supervised information, which will affect the breadth and depth of remote sensing applications.
A3CLNN: Spatial, Spectral and Multiscale Attention ConvLSTM Neural Network for Multisource Remote Sensing Data Classification
The problem of effectively exploiting the information multiple data sources has become a relevant but challenging research topic in remote sensing.
MC-UNet Multi-module Concatenation based on U-shape Network for Retinal Blood Vessels Segmentation
The proposed network structure retains three layers the essential structure of U-Net, in which the atrous convolution combining the multi-kernel pooling blocks are designed to obtain more contextual information.
Semi-Data-Aided Channel Estimation for MIMO Systems via Reinforcement Learning
Data-aided channel estimation is a promising solution to improve channel estimation accuracy by exploiting data symbols as pilot signals for updating an initial channel estimate.
Energy-Efficient IRS-Aided NOMA Beamforming for 6G Wireless Communications
This manuscript presents an energy-efficient alternating optimization framework based on intelligent reflective surfaces (IRS) aided non-orthogonal multiple access beamforming (NOMA-BF) system for 6G wireless communications.
Federated Learning-Based Localization with Heterogeneous Fingerprint Database
Fingerprint-based localization plays an important role in indoor location-based services, where the position information is usually collected in distributed clients and gathered in a centralized server.
Nested Collaborative Learning for Long-Tailed Visual Recognition
NCL consists of two core components, namely Nested Individual Learning (NIL) and Nested Balanced Online Distillation (NBOD), which focus on the individual supervised learning for each single expert and the knowledge transferring among multiple experts, respectively.
Ranked #1 on
Long-tail Learning
on CIFAR-10-LT (ρ=100)
Collaborative Intelligent Reflecting Surface Networks with Multi-Agent Reinforcement Learning
Intelligent reflecting surface (IRS) is envisioned to be widely applied in future wireless networks.
Industrial Style Transfer with Large-scale Geometric Warping and Content Preservation
Given a source product, a target product, and an art style image, our method produces a neural warping field that warps the source shape to imitate the geometric style of the target and a neural texture transformation network that transfers the artistic style to the warped source product.
Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion
Specifically, during pre-training, we simultaneously cover up patches of the panoramic RGB image and sparse depth by shared random mask, then reconstruct the sparse depth in the masked regions.
Universal Segmentation of 33 Anatomies
Firstly, while it is ideal to learn such a model from a large-scale, fully-annotated dataset, it is practically hard to curate such a dataset.
MixCL: Pixel label matters to contrastive learning
It is essential for medical image analysis, which is often notorious for its lack of annotations.
A Deep Learning Approach to Predicting Ventilator Parameters for Mechanically Ventilated Septic Patients
We develop a deep learning approach to predicting a set of ventilator parameters for a mechanically ventilated septic patient using a long and short term memory (LSTM) recurrent neural network (RNN) model.
Vertical Federated Learning: Challenges, Methodologies and Experiments
As a special architecture in FL, vertical FL (VFL) is capable of constructing a hyper ML model by embracing sub-models from different clients.
Locally Random P-adic Alloy Codes with Channel Coding Theorems for Distributed Coded Tensors
We introduce a new metric for analysis called the typical recovery threshold, which focuses on the most likely event and provide a novel construction of distributed coded tensor operations which are optimal with this measure.
Lightweight Projective Derivative Codes for Compressed Asynchronous Gradient Descent
Coded distributed computation has become common practice for performing gradient descent on large datasets to mitigate stragglers and other faults.
Temporal Transformer Networks with Self-Supervision for Action Recognition
The temporal sequence self-supervision module we employ unprecedentedly adopts the streamlined strategy of "random batch random channel" to reverse the sequence of video frames, allowing robust extractions of motion information representation from inversed temporal dimensions and improving the generalization capability of the model.
Which images to label for few-shot medical landmark detection?
We herein propose a novel Sample Choosing Policy (SCP) to select "the most worthy" images for annotation, in the context of few-shot medical landmark detection.
CT-block: a novel local and global features extractor for point cloud
Meanwhile, the transformer-branch performs offset-attention process on the whole point cloud to extract the global feature.
Fast and Light-Weight Network for Single Frame Structured Illumination Microscopy Super-Resolution
In our SF-SIM, we propose a noise estimator which can effectively suppress the noise in the image and enable our method to work under the low light and short exposure environment, without the need for stacking multiple frames for non-local denoising.
RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images
Salient object detection (SOD) for optical remote sensing images (RSIs) aims at locating and extracting visually distinctive objects/regions from the optical RSIs.
$f$-Divergence Thermodynamic Variational Objective: a Deformed Geometry Perspective
In this paper, we propose a $f$-divergence Thermodynamic Variational Objective ($f$-TVO).
Constructing Orthogonal Convolutions in an Explicit Manner
A convolution layer with an orthogonal Jacobian matrix is 1-Lipschitz in the 2-norm, making the output robust to the perturbation in input.
Cooperative Task Offloading and Block Mining in Blockchain-based Edge Computing with Multi-agent Deep Reinforcement Learning
The convergence of mobile edge computing (MEC) and blockchain is transforming the current computing services in mobile networks, by offering task offloading solutions with security enhancement empowered by blockchain mining.
Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration
Based on the reward function, for each state, we then construct a fused score function to evaluate the sampled transformations, where we weight the current and future rewards of the transformations.
iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression
We also propose a lossless compression algorithm based on iVPF.
Elevation Angle-Dependent 3D Trajectory Design for Aerial RIS-aided Communication
This paper investigates an aerial reconfigurable intelligent surface (RIS)-aided communication system under the probabilistic line-of-sight (LoS) channel, where an unmanned aerial vehicle (UAV) equipped with an RIS is deployed to assist two ground nodes in their information exchange.
6G Internet of Things: A Comprehensive Survey
The sixth generation (6G) wireless communication networks are envisioned to revolutionize customer services and applications via the Internet of Things (IoT) towards a future of fully intelligent and autonomous systems.
Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark
Monocular depth estimation aims at predicting depth from a single image or video.
An optical biomimetic eyes with interested object imaging
We presented an optical system to perform imaging interested objects in complex scenes, like the creature easy see the interested prey in the hunt for complex environments.
RigNet: Repetitive Image Guided Network for Depth Completion
Depth completion deals with the problem of recovering dense depth maps from sparse ones, where color images are often used to facilitate this task.
Ranked #2 on
Depth Completion
on KITTI Depth Completion
Joint Communication and Trajectory Design for Intelligent Reflecting Surface Empowered UAV SWIPT Networks
Aiming at the limited battery capacity of widely deployed low-power smart devices in the Internet-of-things (IoT), this paper proposes a novel intelligent reflecting surface (IRS) empowered unmanned aerial vehicle (UAV) simultaneous wireless information and power transfer (SWIPT) network framework, in which IRS is used to reconstruct the wireless channel to enhance the wireless energy transmission efficiency and coverage area of the UAV SWIPT networks.
Low-Latency Federated Learning over Wireless Channels with Differential Privacy
Then, we convert the MAMAB to a max-min bipartite matching problem at each communication round, by estimating rewards with the upper confidence bound (UCB) approach.
IPS300+: a Challenging Multimodal Dataset for Intersection Perception System
Through an IPS (Intersection Perception System) installed at the diagonal of the intersection, this paper proposes a high-quality multimodal dataset for the intersection perception task.
CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography
Spine-related diseases have high morbidity and cause a huge burden of social cost.
Federated Learning for Industrial Internet of Things in Future Industries
The Industrial Internet of Things (IIoT) offers promising opportunities to transform the operation of industrial systems and becomes a key enabler for future industries.
Dynamic network analysis improves protein 3D structural classification
Here, we propose for the first time a way to model 3D structures of proteins as dynamic PSNs, with the hypothesis that this will improve upon the current state-of-the-art PSC approaches that are based on static PSNs (and thus upon the existing state-of-the-art sequence and other 3D structural approaches).
An Extension of BIM Using AI: a Multi Working-Machines Pathfinding Solution
In the practical implementation of a construction site, it is sensible to solve the problem with a hybrid solution; therefore, in our study, we proposed an algorithm based on a cutting-edge multi-pathfinding algorithm to enable the massive number of machines cooperation and offer the advice to modify the unreasonable part of the working site in the meantime.
Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Design
Owing to the low communication costs and privacy-promoting capabilities, Federated Learning (FL) has become a promising tool for training effective machine learning models among distributed clients.
Lite-FPN for Keypoint-based Monocular 3D Object Detection
3D object detection with a single image is an essential and challenging task for autonomous driving.
A lightweight deep learning based cloud detection method for Sentinel-2A imagery fusing multi-scale spectral and spatial features
In the encoder, three input branches are designed to handle spectral bands at their native resolution and extract multiscale spectral features.
ASPCNet: A Deep Adaptive Spatial Pattern Capsule Network for Hyperspectral Image Classification
Based on this observation, this paper proposes an adaptive spatial pattern capsule network (ASPCNet) architecture by developing an adaptive spatial pattern (ASP) unit, that can rotate the sampling location of convolutional kernels on the basis of an enlarged receptive field.
Federated Learning for Internet of Things: A Comprehensive Survey
The Internet of Things (IoT) is penetrating many facets of our daily life with the proliferation of intelligent services and applications empowered by artificial intelligence (AI).
Cross-Validated Tuning of Shrinkage Factors for MVDR Beamforming Based on Regularized Covariance Matrix Estimation
We propose leave-one-out cross-validation (LOOCV) choices for the shrinkage factors to optimize the beamforming performance, referred to as $\text{S}^2$CM-CV and STE-CV.
Action Shuffle Alternating Learning for Unsupervised Action Segmentation
Our SSL trains an RNN to recognize positive and negative action sequences, and the RNN's hidden layer is taken as our new action-level feature embedding.
Potential Convolution: Embedding Point Clouds into Potential Fields
In this work, rather than defining a continuous or discrete kernel, we directly embed convolutional kernels into the learnable potential fields, giving rise to potential convolution.
Anchor-Constrained Viterbi for Set-Supervised Action Segmentation
This paper is about action segmentation under weak supervision in training, where the ground truth provides only a set of actions present, but neither their temporal ordering nor when they occur in a training video.
A novel multimodal fusion network based on a joint coding model for lane line segmentation
There has recently been growing interest in utilizing multimodal sensors to achieve robust lane line segmentation.
Regularized Covariance Estimation for Polarization Radar Detection in Compound Gaussian Sea Clutter
This paper investigates regularized estimation of Kronecker-structured covariance matrices (CM) for polarization radar in sea clutter scenarios where the data are assumed to follow the complex, elliptically symmetric (CES) distributions with a Kronecker-structured CM.
S-AT GCN: Spatial-Attention Graph Convolution Network based Feature Enhancement for 3D Object Detection
3D object detection plays a crucial role in environmental perception for autonomous vehicles, which is the prerequisite of decision and control.
Roles of the Narrow Electronic Band near the Fermi Level in 1$T$-TaS$_2$-Related Layered Materials
4$H_{\rm b}$-TaS$_2$ is a superconducting compound with alternating 1$T$-TaS$_2$ and 1$H$-TaS$_2$ layers, where the 1$H$-TaS$_2$ layer has weak charge density wave (CDW) pattern and reduces the CDW coupling between the adjacent 1$T$-TaS$_2$ layers.
Mesoscale and Nanoscale Physics Materials Science
Multi-Pretext Attention Network for Few-shot Learning with Self-supervision
Self-supervised learning is emerged as an efficient method to utilize unlabeled data.
Effects of Number of Filters of Convolutional Layers on Speech Recognition Model Accuracy
Our results show a strong dependency of word accuracy on the Number of Filters of convolutional layers.
Covert Model Poisoning Against Federated Learning: Algorithm Design and Optimization
An attacker in FL may control a number of participant clients, and purposely craft the uploaded model parameters to manipulate system outputs, namely, model poisoning (MP).
Solving localized wave solutions of the derivative nonlinear Schrodinger equation using an improved PINN method
On the bases of the improved method, the effects for different numbers of initial points sampled, residual collocation points sampled, network layers, neurons per hidden layer on the second order genuine rational soliton solution dynamics of the DNLS are considered, and the relevant analysis when the locally adaptive activation function chooses different initial values of scalable parameters are also exhibited in the simulation of the two-order rogue wave solution.
Pattern Formation and Solitons Exactly Solvable and Integrable Systems
Blockchain Assisted Decentralized Federated Learning (BLADE-FL): Performance Analysis and Resource Allocation
Focusing on this problem, we explore the impact of lazy clients on the learning performance of BLADE-FL, and characterize the relationship among the optimal K, the learning parameters, and the proportion of lazy clients.
Robust Dynamical Decoupling for the Manipulation of a Spin Network via a Single Spin
High-fidelity control of quantum systems is crucial for quantum information processing, but is often limited by perturbations from the environment and imperfections in the applied control fields.
Quantum Physics
Deep Learning to Segment Pelvic Bones: Large-scale CT Datasets and Baseline Models
Due to the lack of a large-scale pelvic CT dataset with annotations, deep learning methods are not fully explored.
Blockchain Assisted Decentralized Federated Learning (BLADE-FL) with Lazy Clients
The proposed BLADE-FL has a good performance in terms of privacy preservation, tamper resistance, and effective cooperation of learning.
Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection
Such a property makes the distribution statistics of a bounding box highly correlated to its real localization quality.
Ranked #38 on
Object Detection
on COCO test-dev
Scalable Federated Learning over Passive Optical Networks
Two-step aggregation is introduced to facilitate scalable federated learning (SFL) over passive optical networks (PONs).
Networking and Internet Architecture
Reconstruction of Quantitative Susceptibility Maps from Phase of Susceptibility Weighted Imaging with Cross-Connected $Ψ$-Net
In this work, we propose to explore a new value of the high-pass filtered phase data generated in susceptibility weighted imaging (SWI), and develop an end-to-end Cross-connected $\Psi$-Net (C$\Psi$-Net) to reconstruct QSM directly from these phase data in SWI without additional pre-processing.
When Federated Learning Meets Blockchain: A New Distributed Learning Paradigm
Motivated by the explosive computing capabilities at end user equipments, as well as the growing privacy concerns over sharing sensitive raw data, a new machine learning paradigm, named federated learning (FL) has emerged.
Networking and Internet Architecture
A Short Review on Data Modelling for Vector Fields
On the application side, vector fields are an extremely useful type of data in empirical sciences, as well as signal processing, e. g. non-parametric transformations of 3D point clouds using 3D vector fields, the modelling of the fluid flow in earth science, and the modelling of physical fields.
Decision-making for Autonomous Vehicles on Highway: Deep Reinforcement Learning with Continuous Action Horizon
Decision-making strategy for autonomous vehicles de-scribes a sequence of driving maneuvers to achieve a certain navigational mission.
LSOTB-TIR:A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark
We evaluate and analyze more than 30 trackers on LSOTB-TIR to provide a series of baselines, and the results show that deep trackers achieve promising performance.
RDP-GAN: A Rényi-Differential Privacy based Generative Adversarial Network
Generative adversarial network (GAN) has attracted increasing attention recently owing to its impressive ability to generate realistic samples with high privacy protection.
An Empirical Comparison of Unsupervised Constituency Parsing Methods
Unsupervised constituency parsing aims to learn a constituency parser from a training corpus without parse tree annotations.
AReLU: Attention-based Rectified Linear Unit
Adding the attention module with a rectified linear unit (ReLU) results in an amplification of positive elements and a suppression of negative ones, both with learned, data-adaptive parameters.
Learning Semantically Enhanced Feature for Fine-Grained Image Classification
We aim to provide a computationally cheap yet effective approach for fine-grained image classification (FGIC) in this letter.
Ranked #7 on
Fine-Grained Image Classification
on Stanford Dogs
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
Specifically, we merge the quality estimation into the class prediction vector to form a joint representation of localization quality and classification, and use a vector to represent arbitrary distribution of box locations.
Ranked #77 on
Object Detection
on COCO test-dev
Reconfigurable Intelligent Surface (RIS)-Enhanced Two-Way OFDM Communications
In this paper, we focus on the reconfigurable intelligent surface (RIS)-enhanced two-way device-to-device (D2D) multi-pair orthogonal-frequency-division-multiplexing (OFDM) communication systems.
DNN-aided Read-voltage Threshold Optimization for MLC Flash Memory with Finite Block Length
The error correcting performance of multi-level-cell (MLC) NAND flash memory is closely related to the block length of error correcting codes (ECCs) and log-likelihood-ratios (LLRs) of the read-voltage thresholds.
Learnable Subspace Clustering
This paper studies the large-scale subspace clustering (LSSC) problem with million data points.
G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes
Counterfactual prediction is a fundamental task in decision-making.
A Compressive Sensing Approach for Federated Learning over Massive MIMO Communication Systems
One major challenge in system design is to reconstruct local gradient vectors accurately at the central server, which are computed-and-sent from the wireless devices.
User-Level Privacy-Preserving Federated Learning: Analysis and Performance Optimization
According to our analysis, the UDP framework can realize $(\epsilon_{i}, \delta_{i})$-LDP for the $i$-th MT with adjustable privacy protection levels by varying the variances of the artificial noise processes.
Set-Constrained Viterbi for Set-Supervised Action Segmentation
This paper is about weakly supervised action segmentation, where the ground truth specifies only a set of actions present in a training video, but not their true temporal ordering.
Vehicle Tracking in Wireless Sensor Networks via Deep Reinforcement Learning
Vehicle tracking has become one of the key applications of wireless sensor networks (WSNs) in the fields of rescue, surveillance, traffic monitoring, etc.
Face Hallucination with Finishing Touches
The coarse-level FHnet generates a frontal coarse HR face and then the fine-level FHnet makes use of the facial component appearance prior, i. e., fine-grained facial components, to attain a frontal HR face image with authentic details.
Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform
We specify two new optimization algorithms: Cayley SGD with momentum, and Cayley ADAM on the Stiefel manifold.
Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation
To tackle intra-class shape variations, we learn canonical shape space (CASS), a unified representation for a large variety of instances of a certain object category.
Recommendations to enhance rigor and reproducibility in biomedical research
Computational methods have reshaped the landscape of modern biology.
UAV-Enabled Confidential Data Collection in Wireless Networks
This work, for the first time, considers confidential data collection in the context of unmanned aerial vehicle (UAV) wireless networks, where the scheduled ground sensor node (SN) intends to transmit confidential information to the UAV without being intercepted by other unscheduled ground SNs.
Naive Gabor Networks for Hyperspectral Image Classification
Specifically, we develop an innovative phase-induced Gabor kernel, which is trickily designed to perform the Gabor feature learning via a linear combination of local low-frequency and high-frequency components of data controlled by the kernel phase.
Curvilinear Distance Metric Learning
To address this issue, we first reveal that the traditional linear distance metric is equivalent to the cumulative arc length between the data pair's nearest points on the learned straight measurer lines.
Lifelong Spectral Clustering
As a new spectral clustering task arrives, L2SC firstly transfers knowledge from both basis library and feature library to obtain encoding matrix, and further redefines the library base over time to maximize performance across all the clustering tasks.
Symplectic $(-2)$-spheres and the symplectomorphism group of small rational 4-manifolds, II
For $(\mathbb{C} P^2 \# 5{\overline {\mathbb{C} P^2}},\omega)$, let $N_{\omega}$ be the number of $(-2)$-symplectic spherical homology classes. We completely determine the Torelli symplectic mapping class group (Torelli SMCG): the Torelli SMCG is trivial if $N_{\omega}>8$; it is $\pi_0(Diff^+(S^2, 5))$ if $N_{\omega}=0$ (by Paul Seidel and Jonathan Evans); it is $\pi_0(Diff^+(S^2, 4))$ in the remaining case.
Symplectic Geometry
Federated Learning with Differential Privacy: Algorithms and Performance Analysis
Specifically, the theoretical bound reveals the following three key properties: 1) There is a tradeoff between the convergence performance and privacy protection levels, i. e., a better convergence performance leads to a lower protection level; 2) Given a fixed privacy protection level, increasing the number $N$ of overall clients participating in FL can improve the convergence performance; 3) There is an optimal number of maximum aggregation times (communication rounds) in terms of convergence performance for a given protection level.
LPRNet: Lightweight Deep Network by Low-rank Pointwise Residual Convolution
To reduce the computation and memory costs, we propose a novel lightweight deep learning module by low-rank pointwise residual (LPR) convolution, called LPRNet.
Bandwidth Slicing to Boost Federated Learning in Edge Computing
Bandwidth slicing is introduced to support federated learning in edge computing to assure low communication delay for training traffic.
Weighted graphlets and deep neural networks for protein structure classification
We develop a weighted network that depicts the protein structures, and more importantly, we propose the first graphlet-based measure that applies to weighted networks.
Weakly Supervised Energy-Based Learning for Action Segmentation
This paper is about labeling video frames with action classes under weak supervision in training, where we have access to a temporal ordering of actions, but their start and end frames in training videos are unknown.
Variable selection with false discovery rate control in deep neural networks
Deep neural networks (DNNs) are famous for their high prediction accuracy, but they are also known for their black-box nature and poor interpretability.
On Safeguarding Privacy and Security in the Framework of Federated Learning
Motivated by the advancing computational capacity of wireless end-user equipment (UE), as well as the increasing concerns about sharing private data, a new machine learning (ML) paradigm has emerged, namely federated learning (FL).
Networking and Internet Architecture
Cross-X Learning for Fine-Grained Visual Categorization
Recognizing objects from subcategories with very subtle differences remains a challenging task due to the large intra-class and small inter-class variation.
Ranked #9 on
Fine-Grained Image Classification
on NABirds
(using extra training data)
Fine-Grained Image Classification
Fine-Grained Visual Categorization
Dense Transformer Networks for Brain Electron Microscopy Image Segmentation
The proposed dense transformer modules are differentiable, thus the entire network can be trained.
Ranked #1 on
Electron Microscopy Image Segmentation
on SNEMI3D
Electron Microscopy Image Segmentation
Semantic Segmentation
Learning Part Generation and Assembly for Structure-aware Shape Synthesis
Enlightened by the fact that 3D shape structure is characterized as part composition and placement, we propose to model 3D shape variations with a part-aware deep generative network, coined as PAGENet.
A Distributed Approach towards Discriminative Distance Metric Learning
Distance metric learning is successful in discovering intrinsic relations in data.
Shakeout: A New Approach to Regularized Deep Neural Network Training
Dropout has played an essential role in many successful deep neural networks, by inducing regularization in the model training.
Pancreas segmentation with probabilistic map guided bi-directional recurrent UNet
To alleviate these problems, we propose a probabilistic-map-guided bi-directional recurrent UNet (PBR-UNet) architecture, which fuses intra-slice information and inter-slice probabilistic maps into a local 3D hybrid regularization scheme, which is followed by bi-directional recurrent network optimization.
A Model-Driven Stack-Based Fully Convolutional Network for Pancreas Segmentation
The irregular geometry and high inter-slice variability in computerized tomography (CT) scans of the human pancreas make an accurate segmentation of this crucial organ a challenging task for existing data-driven deep learning methods.
Privacy Preserving Location Data Publishing: A Machine Learning Approach
By introducing a new formulation of the problem, we are able to apply machine learning algorithms for clustering the trajectories and propose to use $k$-means algorithm for this purpose.
Deep Discriminative Representation Learning with Attention Map for Scene Classification
However, most recent approaches to remote sensing scene classification are based on Convolutional Neural Networks (CNNs).
On Learning and Learned Data Representation by Capsule Networks
In this work, we investigate the following: 1) how the routing affects the CapsNet model fitting; 2) how the representation using capsules helps discover global structures in data distribution, and; 3) how the learned data representation adapts and generalizes to new tasks.
GraphSeq2Seq: Graph-Sequence-to-Sequence for Neural Machine Translation
In this paper, we propose a Graph-Sequence-to-Sequence(GraphSeq2Seq) model to fuse the dependency graph among words into the traditional Seq2Seq framework.
Wide Contextual Residual Network with Active Learning for Remote Sensing Image Classification
As it is very difficult and expensive to obtain class labels in real world, we integrate the proposed WCRN with AL to improve its generalization by using the most informative training samples.
Accurate Spectral Super-resolution from Single RGB Image Using Multi-scale CNN
Different from traditional hyperspectral super-resolution approaches that focus on improving the spatial resolution, spectral super-resolution aims at producing a high-resolution hyperspectral image from the RGB observation with super-resolution in spectral domain.
Predictive Local Smoothness for Stochastic Gradient Methods
To address this problem, we propose a simple yet effective method for improving stochastic gradient methods named predictive local smoothness (PLS).
Privacy Preservation in Location-Based Services: A Novel Metric and Attack Model
In this paper, we incorporate a new type of side information based on consecutive location changes of users and propose a new metric called transition-entropy to investigate the location privacy preservation, followed by two algorithms to improve the transition-entropy for a given dummy generation algorithm.
Generative Steganography by Sampling
In this paper, a new data-driven information hiding scheme called generative steganography by sampling (GSS) is proposed.
Im2Struct: Recovering 3D Shape Structure from a Single RGB Image
We propose to recover 3D shape structures from single RGB images, where structure refers to shape parts represented by cuboids and part relations encompassing connectivity and symmetry.
One-Class Adversarial Nets for Fraud Detection
Currently, most of the fraud detection approaches require a training dataset that contains records of both benign and malicious users.
Adversarial Metric Learning
In distinguishment stage, a metric is exhaustively learned to try its best to distinguish both the adversarial pairs and the original training pairs.
Clustering with Outlier Removal
Then an objective function based Holoentropy is designed to enhance the compactness of each cluster with a few outliers removed.
Quantum Image Processing and Its Application to Edge Detection: Theory and Experiment
Processing of digital images is continuously gaining in volume and relevance, with concomitant demands on data storage, transmission and processing power.
Quantum Physics
Spectrum-based deep neural networks for fraud detection
Due to the small dimension of spectral coordinates (compared with the dimension of the adjacency matrix derived from a graph), training deep neural networks becomes feasible.
Dense Transformer Networks
The proposed dense transformer modules are differentiable, thus the entire network can be trained.
GRASS: Generative Recursive Autoencoders for Shape Structures
We introduce a novel neural network architecture for encoding and synthesis of 3D shapes, particularly their structures.
A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Images
Estimating depth from a single RGB image is an ill-posed and inherently ambiguous problem.
Ranked #34 on
Monocular Depth Estimation
on NYU-Depth V2
ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering
For spectral embedding/clustering, it is still an open problem on how to construct an relation graph to reflect the intrinsic structures in data.
Crowd Counting via Weighted VLAD on Dense Attribute Feature Maps
Crowd counting is an important task in computer vision, which has many applications in video surveillance.
Sparse Deep Stacking Network for Image Classification
Luckily, a simplified neural network module (SNNM) has been proposed to directly learn the discriminative dictionaries for avoiding the expensive inference.
Unsupervised Pretraining Encourages Moderate-Sparseness
It is well known that direct training of deep neural networks will generally lead to poor results.
