Search Results for author:
Found 56 papers, 19 papers with code
Network Pruning by Greedy Subnetwork Selection
Theoretically, we show that the small networks pruned using our method achieve provably lower loss than small networks trained from scratch with the same size.
Unified Source-Free Domain Adaptation
To tackle this unified SFDA problem, we propose a novel approach called Latent Causal Factors Discovery (LCFD).
Source-Free Domain Adaptation with Frozen Multimodal Foundation Model
We find that directly applying the ViL model to the target domain in a zero-shot fashion is unsatisfactory, as it is not specialized for this particular task but largely generic.
Spatial-Temporal Transformer based Video Compression Framework
Similar as the traditional video coding, LVC inherits motion estimation/compensation, residual coding and other modules, all of which are implemented with neural networks (NNs).
MSMix:An Interpolation-Based Text Data Augmentation Method Manifold Swap Mixup
To solve the problem of poor performance of deep neural network models due to insufficient data, a simple yet effective interpolation-based data augmentation method is proposed: MSMix (Manifold Swap Mixup).
Independent Feature Decomposition and Instance Alignment for Unsupervised Domain Adaptation
Existing Unsupervised Domain Adaptation (UDA) methods typically attempt to perform knowledge transfer in a domain-invariant space explicitly or implicitly.
Efficient Transformer-based 3D Object Detection with Dynamic Token Halting
Although halting a token is a non-differentiable operation, our method allows for differentiable end-to-end learning by leveraging an equivalent differentiable forward-pass.
Homeomorphism Alignment for Unsupervised Domain Adaptation
With distribution alignment, it is challenging to acquire a common space which maintains fully the discriminative structure of both domains.
Bit Allocation using Optimization
In this paper, we consider the problem of bit allocation in Neural Video Compression (NVC).
BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach
Bilevel optimization (BO) is useful for solving a variety of important machine learning problems including but not limited to hyperparameter optimization, meta-learning, continual learning, and reinforcement learning.
First Hitting Diffusion Models for Generating Manifold, Graph and Categorical Data
We propose a family of First Hitting Diffusion Models (FHDM), deep generative models that generate data with a diffusion process that terminates at a random first hitting time.
Diffusion-based Molecule Generation with Informative Prior Bridges
AI-based molecule generation provides a promising approach to a large area of biomedical sciences and engineering, such as antibody design, hydrolase engineering, or vaccine development.
Future Gradient Descent for Adapting the Temporal Shifting Data Distribution in Online Recommendation Systems
One of the key challenges of learning an online recommendation model is the temporal domain shift, which causes the mismatch between the training and testing data distribution and hence domain generalization error.
Let us Build Bridges: Understanding and Extending Diffusion Generative Models
Diffusion-based generative models have achieved promising results recently, but raise an array of open questions in terms of conceptual understanding, theoretical analysis, algorithm improvement and extensions to discrete, structured, non-Euclidean domains.
AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results
The homepage of this challenge is at https://github. com/RenYang-home/AIM22_CompressSR.
KUNet: Imaging Knowledge-Inspired Single HDR Image Reconstruction
Recently, with the rise of high dynamic range (HDR) display devices, there is a great demand to transfer traditional low dynamic range (LDR) images into HDR versions.
Multi-Class 3D Object Detection with Single-Class Supervision
While multi-class 3D detectors are needed in many robotics applications, training them with fully labeled datasets can be expensive in labeling cost.
The scope for AI-augmented interpretation of building blueprints in commercial and industrial property insurance
This report, commissioned by the WTW research network, investigates the use of AI in property risk assessment.
NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results
This challenge includes three tracks.
Source-Free Object Detection by Learning To Overlook Domain Style
This approach suffers from both unsatisfactory accuracy of pseudo labels due to the presence of domain shift and limited use of target domain training data.
argmax centroid
We propose a general method to construct centroid approximation for the distribution of maximum points of a random function (a. k. a.
Pareto Navigation Gradient Descent: a First-Order Algorithm for Optimization in Pareto Set
The notion of the Pareto set allows us to focus on the set of (often infinite number of) models that cannot be strictly improved.
Centroid Approximation for Bootstrap: Improving Particle Quality at Inference
In this work, we propose an efficient method to explicitly \emph{optimize} a small set of high quality ``centroid'' points to better approximate the ideal bootstrap distribution.
Pareto Navigation Gradient Descent: a First Order Algorithm for Optimization in Pareto Set
The notion of the Pareto set allows us to focus on the set of (often infinite number of) models that cannot be strictly improved.
MaxUp: Lightweight Adversarial Training With Data Augmentation Improves Neural Network Training
The idea is to generate a set of augmented data with some random perturbations or transforms, and minimize the maximum, or worst case loss over the augmented data.
VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous Treatments
Motivated by the rising abundance of observational data with continuous treatments, we investigate the problem of estimating the average dose-response curve (ADRF).
QoS-aware Link Scheduling Strategy for Data Transmission in SDVN
The original contributions of this paper are summarized as follows: (1) Model the packets collision probability of broadcast or NACK transmission in VANET with the combination theory and investigate the potential influence of miss my packets (MMP) problem.
Networking and Internet Architecture
Varying Coefficient Neural Network with Functional Targeted Regularization for Estimating Continuous Treatment Effects
With the rising abundance of observational data with continuous treatments, we investigate the problem of estimating average dose-response curve (ADRF).
Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough
Despite the great success of deep learning, recent works show that large deep neural networks are often highly redundant and can be significantly reduced in size.
Adaptive Dense-to-Sparse Paradigm for Pruning Online Recommendation System with Non-Stationary Data
To the best of our knowledge, this is the first work to provide in-depth analysis and discussion of applying pruning to online recommendation systems with non-stationary data distribution.
Go Wide, Then Narrow: Efficient Training of Deep Thin Networks
This is achieved by layerwise imitation, that is, forcing the thin network to mimic the intermediate outputs of the wide network from layer to layer.
SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions
For security reasons, it is of critical importance to develop models with certified robustness that can provably guarantee that the prediction is can not be altered by any possible synonymous word substitution.
Unsupervised Feature Selection via Multi-step Markov Transition Probability
Our main contributions are a novel feature section approach which uses multi-step transition probability to characterize the data structure, and three algorithms proposed from the positive and negative aspects for keeping data structure.
Learning Various Length Dependence by Dual Recurrent Neural Networks
Many variants of RNN have been proposed to solve the gradient problems of training RNNs and process long sequences.
Disentanglement Then Reconstruction: Learning Compact Features for Unsupervised Domain Adaptation
By this reconstructor, we can construct prototypes for the original features using class prototypes and domain prototypes correspondingly.
Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting
Recently, Liu et al.[19] proposed a splitting steepest descent (S2D) method that jointly optimizes the neural parameters and architectures based on progressively growing network structures by splitting neurons into multiple copies in a steepest descent fashion.
Joint COCO and Mapillary Workshop at ICCV 2019 Keypoint Detection Challenge Track Technical Report: Distribution-Aware Coordinate Representation for Human Pose Estimation
Taking them together, we formulate a novel Distribution-Aware coordinate Representation for Keypoint (DARK) method.
Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection
This differs from the existing methods based on backward elimination, which remove redundant neurons from the large network.
Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework
Randomized classifiers have been shown to provide a promising approach for achieving certified robustness against adversarial attacks in deep learning.
Stein Self-Repulsive Dynamics: Benefits From Past Samples
Our idea is to introduce Stein variational gradient as a repulsive force to push the samples of Langevin dynamics away from the past trajectories.
Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision
We propose multipoint quantization, a quantization method that approximates a full-precision weight vector using a linear combination of multiple vectors of low-bit numbers; this is in contrast to typical quantization methods that approximate each weight using a single low precision number.
MaxUp: A Simple Way to Improve Generalization of Neural Network Training
The idea is to generate a set of augmented data with some random perturbations or transforms and minimize the maximum, or worst case loss over the augmented data.
Ranked #185 on
Image Classification
on ImageNet
Extended Stochastic Gradient MCMC for Large-Scale Bayesian Variable Selection
Stochastic gradient Markov chain Monte Carlo (MCMC) algorithms have received much attention in Bayesian computing for big data problems, but they are only applicable to a small class of problems for which the parameter space has a fixed dimension and the log-posterior density is differentiable with respect to the parameters.
Distribution-Aware Coordinate Representation for Human Pose Estimation
Interestingly, we found that the process of decoding the predicted heatmaps into the final joint coordinates in the original image space is surprisingly significant for human pose estimation performance, which nevertheless was not recognised before.
Ranked #2 on
Multi-Person Pose Estimation
on MS COCO
(using extra training data)
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
Fast Human Pose Estimation
In this work, we investigate the under-studied but practically critical pose model efficiency problem.
Ranked #9 on
Pose Estimation
on Leeds Sports Poses
Stein Neural Sampler
We propose two novel samplers to generate high-quality samples from a given (un-normalized) probability density.
Variable Selection via Penalized Neural Network: a Drop-Out-One Loss Approach
We propose a variable selection method for high dimensional regression models, which allows for complex, nonlinear, and high-order interactions among variables.
Do Convolutional Neural Networks Learn Class Hierarchy?
We present visual-analytics methods to reveal and analyze this hierarchy of similar classes in relation with CNN-internal data.
Pose-Invariant Face Alignment with a Single CNN
Face alignment has witnessed substantial progress in the last decade.
Ranked #12 on
Facial Landmark Detection
on 300W
3D Reconstruction in the Presence of Glasses by Acoustic and Stereo Fusion
We present a novel sensor fusion algorithm that first segments the depth map into different categories such as opaque/transparent/infinity (e. g., too far to measure) and then updates the depth map based on the segmentation outcome.
Data-driven Flower Petal Modeling with Botany Priors
Each segmented petal is then fitted with a scale-invariant morphable petal shape model, which is constructed from individually scanned exemplar petals.
Real-time Simultaneous Pose and Shape Estimation for Articulated Objects Using a Single Depth Camera
In this paper we present a novel real-time algorithm for simultaneous pose and shape estimation for articulated objects, such as human beings and animals.
Quality Dynamic Human Body Modeling Using a Single Low-cost Depth Camera
In this paper we present a novel autonomous pipeline to build a personalized parametric model (pose-driven avatar) using a single depth sensor.
Video Enhancement of People Wearing Polarized Glasses: Darkening Reversal and Reflection Reduction
With the wide-spread of consumer 3D-TV technology, stereoscopic videoconferencing systems are emerging.
Exploring Social Influence for Recommendation - A Probabilistic Generative Model Approach
The experimental results also confirm that our social influence based group recommendation algorithm outperforms the state-of-the-art algorithms for group recommendation.
