Search Results for author:
Found 100 papers, 35 papers with code
A Mean Field Analysis Of Deep ResNet And Beyond: Towards Provably Optimization Via Overparameterization From Depth
Specifically, we propose a \textbf{new continuum limit} of deep residual networks, which enjoys a good landscape in the sense that \textbf{every local minimizer is global}.
Pillar R-CNN for Point Cloud 3D Object Detection
The performance of point cloud 3D object detection hinges on effectively representing raw points, grid-based voxels or pillars.
Causal-Discovery Performance of ChatGPT in the context of Neuropathic Pain Diagnosis
ChatGPT has demonstrated exceptional proficiency in natural language conversation, e. g., it can answer a wide range of questions while no previous large language models can.
HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awareness
In this paper, from a new perspective, we propose a novel Hierarchical Depth Awareness network (HiDAnet) for RGB-D saliency detection.
Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognition
For face recognition attacks, existing methods typically generate the l_p-norm perturbations on pixels, however, resulting in low attack transferability and high vulnerability to denoising defense models.
Why self-attention is Natural for Sequence-to-Sequence Problems? A Perspective from Symmetries
The knowledge consists of a set of vectors in the same embedding space as the input sequence, containing the information of the language used to process the input sequence.
The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks
We introduce the class of quasi-homogeneous models, which is expressive enough to describe nearly all neural networks with homogeneous activations, even those with biases, residual connections, and normalization layers, while structured enough to enable geometric analysis of its gradient dynamics.
Removing Rain Streaks via Task Transfer Learning
Inspired by our studies, we propose to remove rain by learning favorable deraining representations from other connected tasks.
H2-Stereo: High-Speed, High-Resolution Stereoscopic Video System
We utilize a disparity network to transfer spatiotemporal information across views even in large disparity scenes, based on which, we propose disparity-guided flow-based warping for LSR-HFR view and complementary warping for HSR-LFR view.
AiATrack: Attention in Attention for Transformer Visual Tracking
However, the independent correlation computation in the attention mechanism could result in noisy and ambiguous attention weights, which inhibits further performance improvement.
Ranked #1 on
Visual Object Tracking
on NeedForSpeed
Depth-Adapted CNNs for RGB-D Semantic Segmentation
Recent RGB-D semantic segmentation has motivated research interest thanks to the accessibility of complementary modalities from the input side.
Ranked #22 on
Semantic Segmentation
on NYU Depth v2
Generalization Error Bounds for Deep Neural Networks Trained by SGD
Generalization error bounds for deep neural networks trained by stochastic gradient descent (SGD) are derived by combining a dynamical control of an appropriate parameter norm and the Rademacher complexity estimate based on parameter norms.
Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks
The convergence of GD and SGD when training mildly parameterized neural networks starting from random initialization is studied.
PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection
Real-time and high-performance 3D object detection is of critical importance for autonomous driving.
Beyond the Quadratic Approximation: the Multiscale Structure of Neural Network Loss Landscapes
Numerically, we observe that neural network loss functions possesses a multiscale structure, manifested in two ways: (1) in a neighborhood of minima, the loss mixes a continuum of scales and grows subquadratically, and (2) in a larger region, the loss shows several separate scales clearly.
Exploring Frequency Adversarial Attacks for Face Forgery Detection
In addition, the proposed frequency attack enhances the transferability across face forgery detectors as black-box attacks.
Facial Geometric Detail Recovery via Implicit Representation
Learning a dense 3D model with fine-scale details from a single facial image is highly challenging and ill-posed.
Provably convergent quasistatic dynamics for mean-field two-player zero-sum games
In this paper, we study the problem of finding mixed Nash equilibrium for mean-field two-player zero-sum games.
Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo
Our experiments show that HH-VAEM outperforms existing baselines in the tasks of missing data imputation and supervised learning with missing features.
Deep End-to-end Causal Inference
Causal inference is essential for data-driven decision making across domains such as business engagement, medical treatment and policy making.
LIFT: Learning 4D LiDAR Image Fusion Transformer for 3D Object Detection
LiDAR and camera are two common sensors to collect data in time for 3D object detection under the autonomous driving context.
End-to-End Reconstruction-Classification Learning for Face Forgery Detection
Reconstruction learning over real images enhances the learned representations to be aware of forgery patterns that are even unknown, while classification learning takes the charge of mining the essential discrepancy between real and fake images, facilitating the understanding of forgeries.
Learning Transferable Features for Point Cloud Detection via 3D Contrastive Co-training
First, 3D-CoCo is inspired by our observation that the bird-eye-view (BEV) features are more transferable than low-level geometry features.
Functional Variational Inference based on Stochastic Process Generators
In this paper, we propose a new solution to this problem called Functional Variational Inference (FVI).
Identifiable Generative Models for Missing Not at Random Data Imputation
In this work, we fill in this gap by systematically analyzing the identifiability of generative models under MNAR.
A Riemannian Mean Field Formulation for Two-layer Neural Networks with Batch Normalization
Later, the infinite-width limit of the two-layer neural networks with BN is considered, and a mean-field formulation is derived for the training dynamics.
Modality-Guided Subnetwork for Salient Object Detection
Recent RGBD-based models for saliency detection have attracted research attention.
Learning to Track Objects from Unlabeled Videos
In this paper, we propose to learn an Unsupervised Single Object Tracker (USOT) from scratch.
PointAugmenting: Cross-Modal Augmentation for 3D Object Detection
On one hand, PointAugmenting decorates point clouds with corresponding point-wise CNN features extracted by pretrained 2D detection models, and then performs 3D object detection over the decorated point clouds.
Multi-Decoding Deraining Network and Quasi-Sparsity Based Training
In this work, we aim to exploit the intrinsic priors of rainy images and develop intrinsic loss functions to facilitate training deraining networks, which decompose a rainy image into a rain-free background layer and a rainy layer containing intact rain streaks.
Partial Feature Selection and Alignment for Multi-Source Domain Adaptation
By assuming that the source and target domains share consistent key feature representations and identical label space, existing studies on MSDA typically utilize the entire union set of features from both the source and target domains to obtain the feature map and align the map for each category and domain.
On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework
This paper provides nontrivial results theoretically revealing that, \textit{1}) the cost of achieving perfect perception quality is exactly a doubling of the lowest achievable MSE distortion, \textit{2}) an optimal encoder for the "classic" rate-distortion problem is also optimal for the perceptual compression problem, \textit{3}) distortion loss is unnecessary for training a perceptual decoder.
On Linear Stability of SGD and Input-Smoothness of Neural Networks
The multiplicative structure of parameters and input data in the first layer of neural networks is explored to build connection between the landscape of the loss function with respect to parameters and the landscape of the model function with respect to input data.
Learning Transferable Kinematic Dictionary for 3D Human Pose and Shape Reconstruction
Estimating 3D human pose and shape from a single image is highly under-constrained.
Nonlinear Weighted Directed Acyclic Graph and A Priori Estimates for Neural Networks
In an attempt to better understand structural benefits and generalization power of deep neural networks, we firstly present a novel graph theoretical formulation of neural network models, including fully connected, residual network (ResNet) and densely connected networks (DenseNet).
IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking
Recently, adversarial attack has been applied to visual object tracking to evaluate the robustness of deep trackers.
Continual Learning for Blind Image Quality Assessment
In this paper, we formulate continual learning for BIQA, where a model learns continually from a stream of IQA datasets, building on what was learned from previously seen data.
Achieving Adversarial Robustness Requires An Active Teacher
A new understanding of adversarial examples and adversarial robustness is proposed by decoupling the data generator and the label generator (which we call the teacher).
BSODA: A Bipartite Scalable Framework for Online Disease Diagnosis
To address the challenge, we propose a non-RL Bipartite Scalable framework for Online Disease diAgnosis, called BSODA.
Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning
We then propose to recursively alternate the learning schemes of imitation and exploration to narrow the discrepancy between training and inference.
DEAL: Difficulty-aware Active Learning for Semantic Segmentation
To deal with this problem, we propose a semantic Difficulty-awarE Active Learning (DEAL) network composed of two branches: the common segmentation branch and the semantic difficulty branch.
Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning
The result shows that (1) the escaping time of both SGD and ADAM~depends on the Radon measure of the basin positively and the heaviness of gradient noise negatively; (2) for the same basin, SGD enjoys smaller escaping time than ADAM, mainly because (a) the geometry adaptation in ADAM~via adaptively scaling each gradient coordinate well diminishes the anisotropic structure in gradient noise and results in larger Radon measure of a basin; (b) the exponential gradient average in ADAM~smooths its gradient and leads to lighter gradient noise tails than SGD.
DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs
To minimize the overheads associated with distributed computations, DistDGL uses a high-quality and light-weight min-cut graph partitioning algorithm along with multiple balancing constraints.
Infrared target tracking based on proximal robust principal component analysis method
Infrared target tracking plays an important role in both civil and military fields.
Interpretable Neural Computation for Real-World Compositional Visual Question Answering
There are two main lines of research on visual question answering (VQA): compositional model with explicit multi-hop reasoning, and monolithic network with implicit reasoning in the latent feature space.
Towards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't
The purpose of this article is to review the achievements made in the last few years towards the understanding of the reasons behind the success and subtleties of neural network-based machine learning.
Complexity Measures for Neural Networks with General Activation Functions Using Path-based Norms
The approach is motivated by approximating the general activation functions with one-dimensional ReLU networks, which reduces the problem to the complexity controls of ReLU networks.
A Qualitative Study of the Dynamic Behavior for Adaptive Gradient Algorithms
The dynamic behavior of RMSprop and Adam algorithms is studied through a combination of careful numerical experiments and theoretical explanations.
Cross-Modality 3D Object Detection
In this paper, we focus on exploring the fusion of images and point clouds for 3D object detection in view of the complementary nature of the two modalities, i. e., images possess more semantic information while point clouds specialize in distance sensing.
The Slow Deterioration of the Generalization Error of the Random Feature Model
The random feature model exhibits a kind of resonance behavior when the number of parameters is close to the training sample size.
Rethinking Image Deraining via Rain Streaks and Vapors
Single image deraining regards an input image as a fusion of a background image, a transmission map, rain streaks, and atmosphere light.
Unsupervised Deep Representation Learning for Real-Time Tracking
The advancement of visual tracking has continuously been brought by deep learning models.
Robust Tracking against Adversarial Attacks
On one hand, we add the temporal perturbations into the original video sequences as adversarial examples to greatly degrade the tracking performance.
Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering
However, there are few works studying the data augmentation problem for VQA and none of the existing image based augmentation schemes (such as rotation and flipping) can be directly applied to VQA due to its semantic structure -- an $\langle image, question, answer\rangle$ triplet needs to be maintained correctly.
The Quenching-Activation Behavior of the Gradient Descent Dynamics for Two-layer Neural Network Models
A numerical and phenomenological study of the gradient descent (GD) algorithm for training two-layer neural network models is carried out for different parameter regimes when the target function can be accurately approximated by a relatively small number of neurons.
VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data
Deep generative models often perform poorly in real-world applications due to the heterogeneity of natural data sets.
DGL-KE: Training Knowledge Graph Embeddings at Scale
Experiments on knowledge graphs consisting of over 86M nodes and 338M edges show that DGL-KE can compute embeddings in 100 minutes on an EC2 instance with 8 GPUs and 30 minutes on an EC2 cluster with 4 machines with 48 cores/machine.
Distributed, Parallel, and Cluster Computing
A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth
Specifically, we propose a new continuum limit of deep residual networks, which enjoys a good landscape in the sense that every local minimizer is global.
A Mean-field Analysis of Deep ResNet and Beyond:Towards Provable Optimization Via Overparameterization From Depth
Specifically, we propose a \textbf{new continuum limit} of deep residual networks, which enjoys a good landscape in the sense that \textbf{every local minimizer is global}.
See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks
We introduce a novel network, called CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view.
Semantic Segmentation
Unsupervised Video Object Segmentation
+2
Machine Learning from a Continuous Viewpoint
We demonstrate that conventional machine learning models and algorithms, such as the random feature model, the two-layer neural network model and the residual neural network model, can all be recovered (in a scaled form) as particular discretizations of different continuous formulations.
The Generalization Error of the Minimum-norm Solutions for Over-parameterized Neural Networks
We study the generalization properties of minimum-norm solutions for three over-parametrized machine learning models including the random feature model, the two-layer neural network model and the residual network model.
Deep Image Deraining Via Intrinsic Rainy Image Priors and Multi-scale Auxiliary Decoding
Different rain models and novel network structures have been proposed to remove rain streaks from single rainy images.
Global Convergence of Gradient Descent for Deep Linear Residual Networks
We analyze the global convergence of gradient descent for deep linear residual networks by proposing a new initialization: zero-asymmetric (ZAS) initialization.
HM-VAEs: a Deep Generative Model for Real-valued Data with Heterogeneous Marginals
In this paper, we focused on improving VAEs for real-valued data that has heterogeneous marginal distributions.
Semi-supervised 3D Face Reconstruction with Nonlinear Disentangled Representations
Moreover, the identity and expression representations are entangled in these models, which hurdles many facial editing applications.
Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
Advancing research in the emerging field of deep graph learning requires new tools to support tensor computation over graphs.
Ranked #32 on
Node Classification
on Cora
Real-Time Correlation Tracking via Joint Model Compression and Transfer
In the distillation process, we propose a fidelity loss to enable the student network to maintain the representation capability of the teacher network.
Deep Single Image Deraining Via Estimating Transmission and Atmospheric Light in rainy Scenes
Instead of using the estimated atmospheric light directly to learn a network to calculate transmission, we utilize it as ground truth and design a simple but novel triangle-shaped network structure to learn atmospheric light for every rainy image, then fine-tune the network to obtain a better estimation of atmospheric light during the training of transmission network.
The Barron Space and the Flow-induced Function Spaces for Neural Network Models
We define the Barron space and show that it is the right space for two-layer neural network models in the sense that optimal direct and inverse approximation theorems hold for functions in the Barron space.
A Priori Estimates of the Generalization Error for Two-layer Neural Networks
These new estimates are a priori in nature in the sense that the bounds depend only on some norms of the underlying functions to be fitted, not the parameters in the model.
Analysis of the Gradient Descent Algorithm for a Deep Neural Network Model with Skip-connections
In addition, it is also shown that the GD path is uniformly close to the functions given by the related random feature model.
A Comparative Analysis of the Optimization and Generalization Property of Two-layer Neural Network and Random Feature Models Under Gradient Descent Dynamics
In the over-parametrized regime, it is shown that gradient descent dynamics can achieve zero training loss exponentially fast regardless of the quality of the labels.
Target-Aware Deep Tracking
Despite demonstrated successes for numerous vision tasks, the contributions of using pre-trained deep features for visual tracking are not as significant as that for object recognition.
Depth-Aware Video Frame Interpolation
The proposed model then warps the input frames, depth maps, and contextual features based on the optical flow and local interpolation kernels for synthesizing the output frame.
Ranked #5 on
Video Frame Interpolation
on Middlebury
A Priori Estimates of the Population Risk for Residual Networks
An important part of the regularized model is the usage of a new path norm, called the weighted path norm, as the regularization term.
How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective
The question of which global minima are accessible by a stochastic gradient decent (SGD) algorithm with specific learning rate and batch size is studied from the perspective of dynamical stability.
A Priori Estimates of the Population Risk for Two-layer Neural Networks
New estimates for the population risk are established for two-layer neural networks.
Heterogeneous multireference alignment for images with application to 2-D classification in single particle reconstruction
In this problem, the goal is to estimate a (typically small) set of target images from a (typically large) collection of observations.
Deep Attentive Tracking via Reciprocative Learning
Visual attention, derived from cognitive neuroscience, facilitates human perception on the most pertinent subset of the sensory data.
Person-Job Fit: Adapting the Right Talent for the Right Job with Joint Representation Learning
To this end, in this paper, we propose a novel end-to-end data-driven model based on Convolutional Neural Network (CNN), namely Person-Job Fit Neural Network (PJFNN), for matching a talent qualification to the requirements of a job.
EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE
Many real-life decision-making situations allow further relevant information to be acquired at a specific cost, for example, in assessing the health status of a patient we may decide to take additional measurements such as diagnostic tests or imaging scans before making a final assessment.
Deep Regression Tracking with Shrinkage Loss
Regression trackers directly learn a mapping from regularly dense samples of target objects to soft labels, which are usually generated by a Gaussian function, to estimate target positions.
Model Reduction with Memory and the Machine Learning of Dynamical Systems
The well-known Mori-Zwanzig theory tells us that model reduction leads to memory effect.
Joint Neural Entity Disambiguation with Output Space Search
In this paper, we present a novel model for entity disambiguation that combines both local contextual information and global evidences through Limited Discrepancy Search (LDS).
Variational Implicit Processes
We introduce the implicit processes (IPs), a stochastic process that places implicitly defined multivariate distributions over any finite collections of random variables.
VITAL: VIsual Tracking via Adversarial Learning
To augment positive samples, we use a generative network to randomly generate masks, which are applied to adaptively dropout input features to capture a variety of appearance changes.
CREST: Convolutional Residual Learning for Visual Tracking
Our method integrates feature extraction, response map generation as well as model update into the neural networks for an end-to-end training.
Visual Question Answering with Memory-Augmented Networks
In this paper, we exploit a memory-augmented neural network to predict accurate answers to visual questions, even when those answers occur rarely in the training set.
Robust Visual Tracking via Hierarchical Convolutional Features
Specifically, we learn adaptive correlation filters on the outputs from each convolutional layer to encode the target appearance.
Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking
Second, we learn a correlation filter over a feature pyramid centered at the estimated target position for predicting scale changes.
Video Segmentation via Multiple Granularity Analysis
We introduce a Multiple Granularity Analysis framework for video segmentation in a coarse-to-fine manner.
Person Re-Identification via Recurrent Feature Aggregation
We address the person re-identification problem by effectively exploiting a globally discriminative feature representation from a sequence of tracked human regions/patches.
Learning a No-Reference Quality Metric for Single-Image Super-Resolution
Numerous single-image super-resolution algorithms have been proposed in the literature, but few studies address the problem of performance evaluation based on visual perception.
Deep Extreme Feature Extraction: New MVA Method for Searching Particles in High Energy Physics
Experimental data shows that, DEFE is able to train an ensemble of discriminative feature learners that boosts the overperformance of final prediction.
Hierarchical Convolutional Features for Visual Tracking
The outputs of the last convolutional layers encode the semantic information of targets and such representations are robust to significant appearance variations.
Long-Term Correlation Tracking
In this paper, we address the problem of long-term visual tracking where the target objects undergo significant appearance variation due to deformation, abrupt motion, heavy occlusion and out-of-the-view.
