Search Results for author:
Found 79 papers, 32 papers with code
dS^2LBI: Exploring Structural Sparsity on Deep Network via Differential Inclusion Paths
Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error.
Exploring Label Hierarchy in a Generative Way for Hierarchical Text Classification
Hierarchical Text Classification (HTC), which aims to predict text labels organized in hierarchical space, is a significant task lacking in investigation in natural language processing.
Towards Mitigating Architecture Overfitting in Dataset Distillation
Dataset distillation methods have demonstrated remarkable performance for neural networks trained with very limited training data.
Optimal Sample Selection Through Uncertainty Estimation and Its Application in Deep Learning
Our proposed method, COPS (unCertainty based OPtimal Sub-sampling), is designed to minimize the expected loss of a model trained on subsampled data.
DeepVol: A Deep Transfer Learning Approach for Universal Asset Volatility Modeling
This paper introduces DeepVol, a promising new deep learning volatility model that outperforms traditional econometric models in terms of model generality.
When 3D Bounding-Box Meets SAM: Point Cloud Instance Segmentation with Weak-and-Noisy Supervision
CIP-WPIS leverages pretrained knowledge embedded in the 2D foundation model SAM and 3D geometric prior to achieve accurate point-wise instance labels from the bounding box annotations.
Asymmetric Co-Training with Explainable Cell Graph Ensembling for Histopathological Image Classification
To make full use of pixel-level and cell-level features dynamically, we propose an asymmetric co-training framework combining a deep graph convolutional network and a convolutional neural network for multi-class histopathological image classification.
BAVS: Bootstrapping Audio-Visual Segmentation by Integrating Foundation Knowledge
In a nutshell, our BAVS is designed to eliminate the interference of background noise or off-screen sounds in segmentation by establishing the audio-visual correspondences in an explicit manner.
Audio-Visual Segmentation by Exploring Cross-Modal Mutual Semantics
However, we observed that prior arts are prone to segment a certain salient object in a video regardless of the audio information.
EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation
In this work, we propose EmotionGesture, a novel framework for synthesizing vivid and diverse emotional co-speech 3D gestures from audio.
Self-supervised arbitrary scale super-resolution framework for anisotropic MRI
The anisotropic volume's high-resolution (HR) plane is used to build the HR-LR image pairs for model training.
Deploying Machine Learning Models to Ahead-of-Time Runtime on Edge Using MicroTVM
In the past few years, more and more AI applications have been applied to edge devices.
RFAConv: Innovating Spatial Attention and Standard Convolutional Operation
In this paper, we propose a new perspective on the effectiveness of spatial attention, which is that the spatial attention mechanism essentially solves the problem of convolutional kernel parameter sharing.
Lung Nodule Segmentation and Uncertain Region Prediction with an Uncertainty-Aware Attention Mechanism
Radiologists possess diverse training and clinical experiences, leading to variations in the segmentation annotations of lung nodules and resulting in segmentation uncertainty. Conventional methods typically select a single annotation as the learning target or attempt to learn a latent space comprising multiple annotations.
Diverse 3D Hand Gesture Prediction from Body Dynamics by Bilateral Hand Disentanglement
Considering the asymmetric gestures and motions of two hands, we introduce a Spatial-Residual Memory (SRM) module to model spatial interaction between the body and each hand by residual learning.
Realized recurrent conditional heteroskedasticity model for volatility modelling
We propose a new approach to volatility modelling by combining deep learning (LSTM) and realized volatility measures.
Leveraging Diffusion For Strong and High Quality Face Morphing Attacks
Face morphing attacks seek to deceive a Face Recognition (FR) system by presenting a morphed image consisting of the biometric qualities from two different identities with the aim of triggering a false acceptance with one of the two identities, thereby presenting a significant threat to biometric systems.
Split-PU: Hardness-aware Training Strategy for Positive-Unlabeled Learning
Since only part of the most confident positive samples are available and evidence is not enough to categorize the rest samples, many of these unlabeled data may also be the positive samples.
PatchMix Augmentation to Identify Causal Features in Few-shot Learning
We theoretically show that such an augmentation mechanism, different from existing ones, is able to identify the causal features.
Machine Learning Algorithms for Predicting in-Hospital Mortality in Patients with ST-Segment Elevation Myocardial Infar
Results: A total of 5865 patients with STEMI were enrolled in our study.
Uncertainty-aware Gait Recognition via Learning from Dirichlet Distribution-based Evidence
Existing gait recognition frameworks retrieve an identity in the gallery based on the distance between a probe sample and the identities in the gallery.
Behavior Prior Representation learning for Offline Reinforcement Learning
Our method, Behavior Prior Representation (BPR), learns state representations with an easy-to-integrate objective based on behavior cloning of the dataset: we first learn a state representation by mimicking actions from the dataset, and then train a policy on top of the fixed representation, using any off-the-shelf Offline RL algorithm.
Learning to Learn and Sample BRDFs
We propose a method to accelerate the joint process of physically acquiring and learning neural Bi-directional Reflectance Distribution Function (BRDF) models.
CUTS: A Fully Unsupervised Framework for Medical Image Segmentation
In this work we introduce CUTS (Contrastive and Unsupervised Training for Segmentation), a fully unsupervised deep learning framework for medical image segmentation to better utilize the vast majority of imaging data that is not labeled or annotated.
$\textbf{P$^2$A}$: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos
While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging.
Adversarial Focal Loss: Asking Your Discriminator for Hard Examples
In this paper, we propose a novel adaptation of Focal Loss for keypoint detection tasks, called Adversarial Focal Loss (AFL).
Dual Windows Are Significant: Learning from Mediastinal Window and Focusing on Lung Window
Since the pandemic of COVID-19, several deep learning methods were proposed to analyze the chest Computed Tomography (CT) for diagnosis.
Fast Adversarial Training with Adaptive Step Size
While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet.
Neural Inertial Localization
This paper proposes the inertial localization problem, the task of estimating the absolute location from a sequence of inertial sensor measurements.
Time-coded Spiking Fourier Transform in Neuromorphic Hardware
After several decades of continuously optimizing computing systems, the Moore's law is reaching itsend.
Delving Deeper into Cross-lingual Visual Question Answering
2) We analyze cross-lingual VQA across different question types of varying complexity for different multilingual multimodal Transformers, and identify question types that are the most difficult to improve on.
Robust Binary Models by Pruning Randomly-initialized Networks
In this paper, we introduce an approach to obtain robust yet compact models by pruning randomly-initialized binary networks.
On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training
This lets us show that the decay in generalization performance of adversarial training is a result of the model's attempt to fit hard adversarial instances.
Improving Adversarial Defense with Self-supervised Test-time Fine-tuning
Although adversarial training and its variants currently constitute the most effective way to achieve robustness against adversarial attacks, their poor generalization limits their performance on the test samples.
Hierarchy-Aware T5 with Path-Adaptive Mask Mechanism for Hierarchical Text Classification
Hierarchical Text Classification (HTC), which aims to predict text labels organized in hierarchical space, is a significant task lacking in investigation in natural language processing.
FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution Networks
In natural language processing (NLP), state-of-the-art (SOTA) semi-supervised learning (SSL) frameworks have shown great performance on deep pre-trained language models such as BERT, and are expected to significantly reduce the demand for manual labeling.
Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation
Particularly, we propose a domain translator and align the heterogeneous data to the estimated class prototypes (i. e., class centers) in a hyper-sphere manifold.
Multi-objective Scheduling of Electric Vehicle Charging/Discharging with Time of Use Tariff
Optimal coordinated charging is a multi-objective optimization problem (MOOP) in nature, with objective functions such as minimum price charging and minimum disruptions to the grid.
MG-DVD: A Real-time Framework for Malware Variant Detection Based on Dynamic Heterogeneous Graph Learning
In this paper, we propose MG-DVD, a novel detection framework based on dynamic heterogeneous graph learning, to detect malware variants in real time.
Fourier Transform Approximation as an Auxiliary Task for Image Classification
Image reconstruction is likely the most predominant auxiliary task for image classification, but we would like to think twice about this convention.
An Architecture for Accelerated Large-Scale Inference of Transformer-Based Language Models
We used a BERT model that was fine-tuned for emotion analysis, returning a probability distribution of emotions given a paragraph.
Deep Learning Identifies Neuroimaging Signatures of Alzheimer's Disease Using Structural and Synthesized Functional MRI Data
Here we propose a potential solution by first learning a structural-to-functional transformation in brain MRI, and further synthesizing spatially matched functional images from large-scale structural scans.
Learning Dynamic Alignment via Meta-filter for Few-shot Learning
Our insight is that these methods would lead to poor adaptation with redundant matching, and leveraging channel-wise adjustment is the key to well adapting the learned knowledge to new classes.
Example-based Real-time Clothing Synthesis for Virtual Agents
Given a query shape and pose of the virtual agent, we synthesize the resulting clothing deformation by blending the Taylor expansion results of nearby anchoring points.
Graphics
Beyond COVID-19 Diagnosis: Prognosis with Hierarchical Graph Representation Learning
Our method, combining GCNs and distance aware pooling, can integrate the information from all slices in the chest CT scans for optimal decision making, which leads to the state-of-the-art accuracy in the COVID-19 diagnosis and prognosis.
Revealing the origins of shear band activity and boundary strengthening in polygrain-like architected materials
A recent report on successful employment of the grain boundary strengthening to design extraordinarily damage-tolerant architected materials (i. e. meta-crystals) necessitates fundamental studies to understand the underlying mechanisms responsible for the toughening and high performance of meta-crystals.
Materials Science
Robust Spoken Language Understanding with RL-based Value Error Recovery
The framework consists of a slot tagging model and a rule-based value error recovery module.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Efficient Unpaired Image Dehazing with Cyclic Perceptual-Depth Supervision
Image dehazing without paired haze-free images is of immense importance, as acquiring paired images often entails significant cost.
DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths
Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error.
On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them
We analyze the influence of adversarial training on the loss landscape of machine learning models.
Graph Representation Learning Network via Adaptive Sampling
Graph Attention Network (GAT) and GraphSAGE are neural network architectures that operate on graph-structured data and have been widely studied for link prediction and node classification.
Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing
One daunting problem for semantic parsing is the scarcity of annotation.
Jointly Encoding Word Confusion Network and Dialogue Context with BERT for Spoken Language Understanding
In this paper, a novel BERT based SLU model (WCN-BERT SLU) is proposed to encode WCNs and the dialogue context jointly.
You Only Search Once: A Fast Automation Framework for Single-Stage DNN/Accelerator Co-design
DNN/Accelerator co-design has shown great potential in improving QoR and performance.
Instance Credibility Inference for Few-Shot Learning
To measure the credibility of each pseudo-labeled instance, we then propose to solve another linear regression hypothesis by increasing the sparsity of the incidental parameters and rank the pseudo-labeled instances with their sparsity degree.
Segmentation with Residual Attention U-Net and an Edge-Enhancement Approach Preserves Cell Shape Features
The ability to extrapolate gene expression dynamics in living single cells requires robust cell segmentation, and one of the challenges is the amorphous or irregularly shaped cell boundaries.
Substituting Gadolinium in Brain MRI Using DeepContrast
Together, these studies validate our hypothesis that a deep learning approach can potentially replace the need for GBCAs in brain MRI.
Training Provably Robust Models by Polyhedral Envelope Regularization
Training certifiable neural networks enables one to obtain models with robustness guarantees against adversarial attacks.
Exploring Multilingual Syntactic Sentence Representations
We study methods for learning sentence embeddings with syntactic structure.
DENS: A Dataset for Multi-class Emotion Analysis
Our results show that the dataset provides a novel opportunity in emotion analysis that requires moving beyond existing sentence-level techniques.
Boosting Network: Learn by Growing Filters and Layers via SplitLBI
Network structures are important to learning good representations of many tasks in computer vision and machine learning communities.
Split LBI for Deep Learning: Structural Sparsity via Differential Inclusion Paths
Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error.
Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path
This paper proposes a new approach for automated floorplan reconstruction from RGBD scans, a major milestone in indoor mapping research.
Semantic Parsing with Dual Learning
Semantic parsing converts natural language queries into structured logical forms.
Coherent and Controllable Outfit Generation
A user study suggests that people understand the match between the queries and the outfits produced by our method.
Exploring Structural Sparsity of Deep Networks via Inverse Scale Spaces
To fill in this gap, this paper proposes a new approach based on differential inclusions of inverse scale spaces, which generate a family of models from simple to complex ones along the dynamics via coupling a pair of parameters, such that over-parameterized deep models and their structural sparsity can be explored simultaneously.
On Certifying Non-uniform Bound against Adversarial Attacks
This work studies the robustness certification problem of neural network models, which aims to find certified adversary-free regions as large as possible around data points.
MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation
We propose a new approach for 3D instance segmentation based on sparse convolution and point affinity prediction, which indicates the likelihood of two points belonging to the same instance.
Ranked #1 on
3D Instance Segmentation
on ScanNet
Deep Heterogeneous Autoencoders for Collaborative Filtering
This paper leverages heterogeneous auxiliary information to address the data sparsity problem of recommender systems.
PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image
This paper proposes a deep neural architecture, PlaneRCNN, that detects and reconstructs piecewise planar surfaces from a single RGB image.
Finding Mixed Nash Equilibria of Generative Adversarial Networks
We reconsider the training objective of Generative Adversarial Networks (GANs) from the mixed Nash Equilibria (NE) perspective.
PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image
The proposed end-to-end DNN learns to directly infer a set of plane parameters and corresponding plane segmentation masks from a single RGB image.
Ranked #2 on
Plane Instance Segmentation
on NYU Depth v2
FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans
The ultimate goal of this indoor mapping research is to automatically reconstruct a floorplan simply by walking through a house with a smartphone in a pocket.
Teaching Autonomous Driving Using a Modular and Integrated Approach
Then, once the students have understood these modules, the experimental platforms for integration we have developed allow the students to fully understand how the modules interact with each other.
Raster-To-Vector: Revisiting Floorplan Transformation
A neural architecture first transforms a rasterized image to a set of junctions that represent low-level geometric and semantic information (e. g., wall corners or door end-points).
Deep Multi-Modal Image Correspondence Learning
Our result implies that neural networks are effective at perceptual tasks that require long periods of reasoning even for humans to solve.
Multi-way Particle Swarm Fusion
This paper proposes a novel MAP inference framework for Markov Random Field (MRF) in parallel computing environments.
Layered Scene Decomposition via the Occlusion-CRF
This paper addresses the challenging problem of perceiving the hidden or occluded geometry of the scene depicted in any given RGBD image.
Driving rate dependence of avalanche statistics and shapes at the yielding transition
We study stress time series caused by plastic avalanches in athermally sheared disordered materials.
Soft Condensed Matter Statistical Mechanics
