Search Results for author:
Found 120 papers, 41 papers with code
TopoGAN: A Topology-Aware Generative Adversarial Network
We show in experiments that our method generates synthetic images with realistic topology.
Rate-Perception Optimized Preprocessing for Video Coding
In the past decades, lots of progress have been done in the video compression field including traditional video codec and learning-based video codec.
Robust Ranking Explanations
Gradient-based explanation is the cornerstone of explainable deep networks, but it has been shown to be vulnerable to adversarial attacks.
DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization
LiDAR mapping is important yet challenging in self-driving and mobile robotics.
FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning
Most existing methods focus on learning noise-robust models from web images while neglecting the performance drop caused by the differences between web domain and real-world domain.
From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-Resolution
In the fine area, we use an Intra-Patch Self-Attention (IPSA) module to model long-range pixel dependencies in a local patch, and then a $3\times3$ convolution is applied to process the finest details.
Backdoor Cleansing with Unlabeled Data
It is crucial to defend against such attacks, i. e., to postprocess a suspicious model so that its backdoor behavior is mitigated while its normal prediction power on clean inputs remain uncompromised.
ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement
In this paper, we propose an efficient structure named Efficient Correspondence Transformer (ECO-TR) by finding correspondences in a coarse-to-fine manner, which significantly improves the efficiency of functional correspondence model.
Feedback Stability Analysis via Dissipativity with Dynamic Supply Rates
In this paper, we propose a notion of dissipativity with dynamic supply rates for nonlinear differential input-state-output equations via the use of auxiliary systems.
Deep Anomaly Detection and Search via Reinforcement Learning
Semi-supervised Anomaly Detection (AD) is a kind of data mining task which aims at learning features from partially-labeled datasets to help detect outliers.
Self-Supervised Visual Place Recognition by Mining Temporal and Feature Neighborhoods
Inspired by noisy label learning, we propose a novel self-supervised framework named \textit{TF-VPR} that uses temporal neighborhoods and learnable feature neighborhoods to discover unknown spatial neighborhoods.
A Multimodal Transformer: Fusing Clinical Notes with Structured EHR Data for Interpretable In-Hospital Mortality Prediction
Deep-learning-based clinical decision support using structured electronic health records (EHR) has been an active research area for predicting risks of mortality and diseases.
HOB-CNN: Hallucination of Occluded Branches with a Convolutional Neural Network for 2D Fruit Trees
We further validated HOB-CNN against two different types of 2D trees, and HOB-CNN shows generalization across different trees and robustness under different occluded conditions.
Learning Topological Interactions for Multi-Class Medical Image Segmentation
In this paper, we introduce a novel topological interaction module to encode the topological interactions into a deep neural network.
UniFormer: Unified Multi-view Fusion Transformer for Spatial-Temporal Representation in Bird's-Eye-View
Bird's eye view (BEV) representation is a new perception formulation for autonomous driving, which is based on spatial fusion.
Latent Partition Implicit with Surface Codes for 3D Representation
Our insight here is that both the part learning and the part blending can be conducted much easier in the latent space than in the spatial space.
Hiding Your Signals: A Security Analysis of PPG-based Biometric Authentication
It reduces the success rate of rPPG spoofing attacks in user authentication to 0. 05.
MDOE: A Spatiotemporal Event Representation Considering the Magnitude and Density of Events
Event-based sensors (e. g., DVS cameras) are capable of higher dynamic range, higher temporal resolution, lower time latency, and better power efficiency compared to conventional devices (e. g., RGB cameras).
On the Convergence of Optimizing Persistent-Homology-Based Losses
Topological loss based on persistent homology has shown promise in various applications.
Learning Probabilistic Topological Representations Using Discrete Morse Theory
We use discrete Morse theory and persistent homology to construct an one-parameter family of structures as the topological/structural representation space.
Nuclear Norm Maximization Based Curiosity-Driven Learning
To handle the sparsity of the extrinsic rewards in reinforcement learning, researchers have proposed intrinsic reward which enables the agent to learn the skills that might come in handy for pursuing the rewards in the future, such as encouraging the agent to visit novel states.
A Study of the Attention Abnormality in Trojaned BERTs
Trojan attacks raise serious security concerns.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
A Novel Framework for Characterization of Tumor-Immune Spatial Relationships in Tumor Microenvironment
Understanding the impact of tumor biology on the composition of nearby cells often requires characterizing the impact of biologically distinct tumor regions.
Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation
Capturing the dynamics in user preference is crucial to better predict user future behaviors because user preferences often drift over time.
PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation
Pixel synthesis is a promising research paradigm for image generation, which can well exploit pixel-wise prior knowledge for generation.
End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillation
Extensive experiments on HICO-Det dataset demonstrate that our model discovers potential interactive pairs and enables the recognition of unseen HOIs.
Human-Object Interaction Detection
Knowledge Distillation
+3
Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation
User interests are usually dynamic in the real world, which poses both theoretical and practical challenges for learning accurate preferences from rich behavior data.
SeqTR: A Simple yet Universal Network for Visual Grounding
In this paper, we propose a simple yet universal network termed SeqTR for visual grounding tasks, e. g., phrase localization, referring expression comprehension (REC) and segmentation (RES).
Discovering Governing Equations by Machine Learning implemented with Invariance
The partial differential equation (PDE) plays a significantly important role in many fields of science and engineering.
A Manifold View of Adversarial Risk
Assuming data lies in a manifold, we investigate two new types of adversarial risk, the normal adversarial risk due to perturbation along normal direction, and the in-manifold adversarial risk due to perturbation within the manifold.
Temporal Context Matters: Enhancing Single Image Prediction with Disease Progression Representations
In our method, a self-attention based Temporal Convolutional Network (TCN) is used to learn a representation that is most reflective of the disease trajectory.
A Topology-Attention ConvLSTM Network and Its Application to EM Images
We propose a novel TopologyAttention ConvLSTM Network (TACNet) for 3D image segmentation in order to achieve high structural accuracy for 3D segmentation tasks.
Neural Approximation of Graph Topological Features
Topological features based on persistent homology capture high-order structural information so as to augment graph neural network methods.
Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation
To address this problem, we propose Resistance Training using Prior Bias (RTPB) for the scene graph generation.
DIFNet: Boosting Visual Information Flow for Image Captioning
Current Image captioning (IC) methods predict textual words sequentially based on the input visual information from the visual feature extractor and the partially generated sentence information.
Geometry-Aware Fruit Grasping Estimation for Robotic Harvesting in Orchards
It is vital for robots to recognise and localise fruits before the harvesting in natural orchards.
A General Framework for Debiasing in CTR Prediction
Most of the existing methods for debaising in click-through rate (CTR) prediction depend on an oversimplified assumption, i. e., the click probability is the product of observation probability and relevance probability.
Multi-objective Explanations of GNN Predictions
We design a user study to investigate such joint effects and use the findings to design a multi-objective optimization (MOO) algorithm to find Pareto optimal explanations that are well-balanced in simulatability and counterfactual.
Federated Learning with Domain Generalization
Federated Learning (FL) enables a group of clients to jointly train a machine learning model with the help of a centralized server.
R4: A Framework for Route Representation and Route Recommendation
For user representation, we utilize a series of historical navigation to extract user preference.
Trigger Hunting with a Topological Prior for Trojan Detection
Despite their success and popularity, deep neural networks (DNNs) are vulnerable when facing backdoor attacks.
Multi-Class Cell Detection Using Spatial Context Representation
In digital pathology, both detection and classification of cells are important for automatic diagnostic and prognostic tasks.
Cycle Representation Learning for Inductive Relation Prediction
In this paper, we consider rules as cycles and show that the space of cycles has a unique structure based on the mathematics of algebraic topology.
A Frequency-Domain Approach to Nonlinear Negative Imaginary Systems Analysis
In this study, we extend the theory of negative imaginary (NI) systems to a nonlinear framework using a frequency-domain approach.
A Topological View of Rule Learning in Knowledge Graphs
We propose to collect cycle bases that span the space of cycles.
DNBP: Differentiable Nonparametric Belief Propagation
By combining differentiable neural networks with an efficient belief propagation algorithm, our method learns to maintain a set of marginal posterior samples using end-to-end training.
Learning to Abstain in the Presence of Uninformative Data
Learning and decision making in domains with naturally high noise-to-signal ratios – such as Finance or Public Health – can be challenging and yet extremely important.
Self-learn to Explain Siamese Networks Robustly
Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and imbalanced.
The Singular Angle of Nonlinear Systems
It is, thus, different from the recently appeared nonlinear system phase which adopts the complexification of real-valued signals using the Hilbert transform.
Topological Detection of Trojaned Neural Networks
Deep neural networks are known to have security issues.
Convolutional Block Design for Learned Fractional Downsampling
The layers of convolutional neural networks (CNNs) can be used to alter the resolution of their inputs, but the scaling factors are limited to integer values.
Scalable and Explainable 1-Bit Matrix Completion via Graph Signal Learning
One-bit matrix completion is an important class of positiveunlabeled (PU) learning problems where the observations consist of only positive examples, eg, in top-N recommender systems.
TopoTxR: A Topological Biomarker for Predicting Treatment Response in Breast Cancer
Characterization of breast parenchyma on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a challenging task owing to the complexity of underlying tissue structures.
Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
This survey presents the most recent findings of privacy attacks and defenses appeared in cloud-based neural network services.
Structure Guided Lane Detection
Next, multi-level structural constraints are used to improve the perception of lanes.
Ranked #15 on
Lane Detection
on CULane
NeuSE: A Neural Snapshot Ensemble Method for Collaborative Filtering
In collaborative filtering (CF) algorithms, the optimal models are usually learned by globally minimizing the empirical risks averaged over all the observed data.
Synthesizing MR Image Contrast Enhancement Using 3D High-resolution ConvNets
To alleviate the data imbalance problem between normal tissues and the tumor regions, we introduce a local loss to improve the contribution of the tumor regions, which leads to better enhancement results on tumors.
Topology-Aware Segmentation Using Discrete Morse Theory
In the segmentation of fine-scale structures from natural and biomedical images, per-pixel accuracy is not the only metric of concern.
Learning with Feature-Dependent Label Noise: A Progressive Approach
Label noise is frequently observed in real-world large-scale datasets.
Ranked #8 on
Learning with noisy labels
on ANIMAL
Compiler-Guided Throughput Scheduling for Many-core Machines
Typical schedulers in multi-tenancy environments make use of reactive, feedback-oriented mechanisms based on performance counters to avoid resource contention but suffer from detection lag and loss of performance.
Distributed, Parallel, and Cluster Computing
Link Prediction with Persistent Homology: An Interactive View
Link prediction is an important learning task for graph-structured data.
Machine Learning Based Cyber Attacks Targeting on Controlled Information: A Survey
Stealing attack against controlled information, along with the increasing number of information leakage incidents, has become an emerging cyber security threat in recent years.
Stability of SGD: Tightness Analysis and Improved Bounds
This raises the question: is the stability analysis of [18] tight for smooth functions, and if not, for what kind of loss functions and data distributions can the stability analysis be improved?
Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach
A federatedGAN jointly trains a centralized generator and multiple private discriminators hosted at different sites.
Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projections Matching
Our method pushes the neural network to generate a 3D point cloud whose 2D projections match the irregular point supervision from different view angles.
Ricci-GNN: Defending Against Structural Attacks Through a Geometric Approach
We propose a novel GNN defense algorithm against structural attacks that maliciously modify graph topology.
Revisiting the Stability of Stochastic Gradient Descent: A Tightness Analysis
We provide empirical evidence that this condition holds for several loss functions, and provide theoretical evidence that the known tight SGD stability bounds for convex and non-convex loss functions can be circumvented by HC loss functions, thus partially explaining the generalization of deep neural networks.
Localization in the Crowd with Topological Constraints
Due to various challenges, a localization method is prone to spatial semantic errors, i. e., predicting multiple dots within a same person or collapsing multiple dots in a cluttered region.
A Topological Filter for Learning with Label Noise
Noisy labels can impair the performance of deep neural networks.
Phase of Nonlinear Systems
A nonlinear small phase theorem is then established for feedback stability analysis of semi-sectorial systems.
Error-Bounded Correction of Noisy Labels
To be robust against label noise, many successful methods rely on the noisy classifiers (i. e., models trained on the noisy training data) to determine whether a label is trustworthy.
Ranked #38 on
Image Classification
on Clothing1M
RCHOL: Randomized Cholesky Factorization for Solving SDD Linear Systems
We introduce a randomized algorithm, namely RCHOL, to construct an approximate Cholesky factorization for a given Laplacian matrix (a. k. a., graph Laplacian).
Numerical Analysis Mathematical Software Numerical Analysis
Minimizing Labeling Effort for Tree Skeleton Segmentation using an Automated Iterative Training Methodology
It is shown that in our application, the new Automating-the-Loop method greatly reduces the labeling effort while producing comparable performance to both human-in-the-loop and complete manual labeling methods.
Semantic Segmentation for Partially Occluded Apple Trees Based on Deep Learning
DeepLabv3 outperforms the other models at Binary accuracy, Mean IoU and Boundary F1 score, but is surpassed by Pix2Pix (without discriminator) and U-Net in Occluded branch recall.
Deep Variational Instance Segmentation
Specifically, we propose a variational relaxation of instance segmentation as minimizing an optimization functional for a piecewise-constant segmentation problem, which can be used to train an FCN end-to-end.
Object Tracking by Least Spatiotemporal Searches
This paper proposes a strategy named IHMs (Intermediate Searching at Heuristic Moments): each step we figure out which moment is the best to search according to a heuristic indicator, then at that moment search locations one by one in descending order of predicted appearing probabilities, until a search hits; iterate this step until we get the object's current location.
Learn distributed GAN with Temporary Discriminators
Our proposed method tackles the challenge of training GAN in the federated learning manner: How to update the generator with a flow of temporary discriminators?
DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Images
To optimize 3D shape parameters, current renderers rely on pixel-wise losses between rendered images of 3D reconstructions and ground truth images from corresponding viewpoints.
End-to-End AI-Based Point-of-Care Diagnosis System for Classifying Respiratory Illnesses and Early Detection of COVID-19
Respiratory symptoms can be a caused by different underlying conditions, and are often caused by viral infections, such as Influenza-like illnesses or other emerging viruses like the Coronavirus.
Local Causal Structure Learning and its Discovery Between Type 2 Diabetes and Bone Mineral Density
To illustrate the importance of prior knowledge, the result of the algorithm without prior knowledge is also investigated.
Attention-Guided Discriminative Region Localization and Label Distribution Learning for Bone Age Assessment
However, training with the global image underutilizes discriminative local information, while providing extra annotations is expensive and subjective.
Synthetic Learning: Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image Data
In this paper, we propose a data privacy-preserving and communication efficient distributed GAN learning framework named Distributed Asynchronized Discriminator GAN (AsynDGAN).
Rigorous Explanation of Inference on Probabilistic Graphical Models
There is no existing method to rigorously attribute the inference outcomes to the contributing factors of the graphical models.
Real-Time Fruit Recognition and Grasping Estimation for Autonomous Apple Harvesting
In this research, a fully neural network based visual perception framework for autonomous apple harvesting is proposed.
Visual Perception and Modelling in Unstructured Orchard for Apple Harvesting Robots
This paper develops a framework of visual perception and modelling for robotic harvesting of fruits in the orchard environments.
HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation
In particular, our proposed HoMM can perform arbitrary-order moment tensor matching, we show that the first-order HoMM is equivalent to Maximum Mean Discrepancy (MMD) and the second-order HoMM is equivalent to Correlation Alignment (CORAL).
Fruit Detection, Segmentation and 3D Visualisation of Environments in Apple Orchards
The robustness and efficiency of the DaSNet-V2 in detection and segmentation are validated by the experiments in the real-environment of apple orchard.
Point Cloud Processing via Recurrent Set Encoding
The spatial layout of the beams is regular, and this allows the beam features to be further fed into an efficient 2D convolutional neural network (CNN) for hierarchical feature aggregation.
SSAH: Semi-supervised Adversarial Deep Hashing with Self-paced Hard Sample Generation
In this paper, we propose a novel Semi-supervised Self-pace Adversarial Hashing method, named SSAH to solve the above problems in a unified framework.
Label Cleaning with Likelihood Ratio Test
To collect large scale annotated data, it is inevitable to introduce label noise, i. e., incorrect class labels.
A Predictive On-Demand Placement of UAV Base Stations Using Echo State Network
In this paper, we propose a system framework consisting of UEs clustering, UAV-BS placement, UEs trajectories prediction, and UAV-BS reposition matching scheme, to serve the UEs seamlessly as well as minimize the energy cost of UAV-BSs' reposition trajectories.
Scalable Explanation of Inferences on Large Graphs
Probabilistic inferences distill knowledge from graphs to aid human make important decisions.
From Crowdsourcing to Crowdmining: Using Implicit Human Intelligence for Better Understanding of Crowdsourced Data
A generic model for CrowdMining is further proposed based on a set of existing studies.
ShapeCaptioner: Generative Caption Network for 3D Shapes by Learning a Mapping from Parts Detected in Multiple Views to Sentences
Specifically, ShapeCaptioner aggregates the parts detected in multiple colored views using our novel part class specific aggregation to represent a 3D shape, and then, employs a sequence to sequence model to generate the caption.
Learning from Thresholds: Fully Automated Classification of Tumor Infiltrating Lymphocytes for Multiple Cancer Types
This allows for a much larger training set, that reflects visual variability across multiple cancer types and thus training of a single network which can be automatically applied to each cancer type without human adjustment.
Topology-Preserving Deep Image Segmentation
Segmentation algorithms are prone to make topological errors on fine-scale structures, e. g., broken connections.
DeepSquare: Boosting the Learning Power of Deep Convolutional Neural Networks with Elementwise Square Operators
In this paper, we pursue very efficient neural network modules which can significantly boost the learning power of deep convolutional neural networks with negligible extra computational cost.
ClusterNet: Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud Analysis
Current neural networks for 3D object recognition are vulnerable to 3D rotation.
Selective Transfer with Reinforced Transfer Network for Partial Domain Adaptation
However, since the domain shift between source and target domains, only using the deep features for sample selection is defective.
Ranked #5 on
Partial Domain Adaptation
on Office-31
Automatic Long-Term Deception Detection in Group Interaction Videos
Most work on automated deception detection (ADD) in video has two restrictions: (i) it focuses on a video of one person, and (ii) it focuses on a single act of deception in a one or two minute video.
Strain engineering of epitaxial oxide heterostructures beyond substrate limitations
The limitation of commercially available single-crystal substrates and the lack of continuous strain tunability preclude the ability to take full advantage of strain engineering for further exploring novel properties and exhaustively studying fundamental physics in complex oxides.
Materials Science
Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation
Recent advances in unsupervised domain adaptation mainly focus on learning shared representations by global distribution alignment without considering class information across domains.
PBBFMM3D: a parallel black-box algorithm for kernel matrix-vector multiplication
We introduce a parallel method that provably requires $O(N)$ operations to reduce the computation cost.
Mathematical Software
An Algebraic Sparsified Nested Dissection Algorithm Using Low-Rank Approximations
We evaluate the algorithm on some large problems show it exhibits near-linear scaling.
Numerical Analysis
Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functions
Three-dimensional object recognition has recently achieved great progress thanks to the development of effective point cloud-based learning frameworks, such as PointNet and its extensions.
Learning to Detect Instantaneous Changes with Retrospective Convolution and Static Sample Synthesis
Change detection has been a challenging visual task due to the dynamic nature of real-world scenes.
Collaborative Filtering with Stability
Collaborative filtering (CF) is a popular technique in today's recommender systems, and matrix approximation-based CF methods have achieved great success in both rating prediction and top-N recommendation tasks.
Parameter Transfer Extreme Learning Machine based on Projective Model
Unlike the existing parameter transfer approaches, which incorporate the source model information into the target by regularizing the di erence between the source and target domain parameters, an intuitively appealing projective-model is proposed to bridge the source and target model parameters.
Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation
Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities.
A Topological Regularizer for Classifiers via Persistent Homology
In particular, our measurement of topological complexity incorporates the importance of topological features (e. g., connected components, handles, and so on) in a meaningful manner, and provides a direct control over spurious topological structures.
An Approximate Bayesian Long Short-Term Memory Algorithm for Outlier Detection
In this study, we propose an approximate estimation of the weights uncertainty using Ensemble Kalman Filter, which is easily scalable to a large number of weights.
Mixture-Rank Matrix Approximation for Collaborative Filtering
However, our studies show that submatrices with different ranks could coexist in the same user-item rating matrix, so that approximations with fixed ranks cannot perfectly describe the internal structures of the rating matrix, therefore leading to inferior recommendation accuracy.
Ranked #4 on
Recommendation Systems
on MovieLens 10M
Multiple Instance Hybrid Estimator for Hyperspectral Target Characterization and Sub-pixel Target Detection
The Multiple Instance Hybrid Estimator for discriminative target characterization from imprecisely labeled hyperspectral data is presented.
Composing Tree Graphical Models with Persistent Homology Features for Clustering Mixed-Type Data
Clustering data with both continuous and discrete attributes is a challenging task.
Partial Membership Latent Dirichlet Allocation
Topic models (e. g., pLSA, LDA, sLDA) have been widely used for segmenting imagery.
Partial Membership Latent Dirichlet Allocation
Topic models (e. g., pLSA, LDA, SLDA) have been widely used for segmenting imagery.
Mode Estimation for High Dimensional Discrete Tree Graphical Models
Though the mode finding problem is generally intractable in high dimensions, this paper unveils that, if the distribution can be approximated well by a tree graphical model, mode characterization is significantly easier.
