Search Results for author:
Found 58 papers, 16 papers with code
Learning to Segment 3D Point Clouds in 2D Image Space
In contrast to the literature where local patterns in 3D point clouds are captured by customized convolutional operators, in this paper we study the problem of how to effectively and efficiently project such point clouds into a 2D image space so that traditional 2D convolutional neural networks (CNNs) such as U-Net can be applied for segmentation.
Deep Lucas-Kanade Homography for Multimodal Image Alignment
With those properties, directly updating the Lucas-Kanade algorithm on our feature maps will precisely align image pairs with large appearance changes.
A Surface Geometry Model for LiDAR Depth Completion
Therefore, it is assumed those pixels share the same surface with the nearest LiDAR point, and their respective depth can be estimated as the nearest LiDAR depth value plus a residual error.
Robust Object Detection With Inaccurate Bounding Boxes
As the crowd-sourcing labeling process and the ambiguities of the objects may raise noisy bounding box annotations, the object detectors will suffer from the degenerated training data.
$f$-GAIL: Learning $f$-Divergence for Generative Adversarial Imitation Learning
This naturally gives rise to the following question: Given a set of expert demonstrations, which divergence can recover the expert policy more accurately with higher data efficiency?
RNNs Incrementally Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients?
Recurrent neural networks (RNNs) are particularly well-suited for modeling long-term dependencies in sequential data, but are notoriously hard to train because the error backpropagated in time either vanishes or explodes at an exponential rate.
Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients
Deep neural networks for 3D point cloud classification, such as PointNet, have been demonstrated to be vulnerable to adversarial attacks.
Self-supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and Beyond
To learn distinguishable patterns, most of recent works in vehicle re-identification (ReID) struggled to redevelop official benchmarks to provide various supervisions, which requires prohibitive human labors.
Don't Knock! Rowhammer at the Backdoor of DNN Models
To this end, we first investigate the viability of backdoor injection attacks in real-life deployments of DNNs on hardware and address such practical issues in hardware implementation from a novel optimization perspective.
Self-supervised Geometric Features Discovery via Interpretable Attentio for Vehicle Re-Identification and Beyond (Complete Version)
To learn distinguishable patterns, most of recent works in vehicle re-identification (ReID) struggled to redevelop official benchmarks to provide various supervisions, which requires prohibitive human labors.
White-Box Adversarial Defense via Self-Supervised Data Estimation
In this paper, we study the problem of how to defend classifiers against adversarial attacks that fool the classifiers using subtly modified input data.
TreeRNN: Topology-Preserving Deep GraphEmbedding and Learning
General graphs are difficult for learning due to their irregular structures.
Training Deep Neural Networks via Branch-and-Bound
In this paper, we propose BPGrad, a novel approximate algorithm for deep nueral network training, based on adaptive estimates of feasible region via branch-and-bound.
Deformable Part Networks
In this paper we propose novel Deformable Part Networks (DPNs) to learn {\em pose-invariant} representations for 2D object recognition.
LMKL-Net: A Fast Localized Multiple Kernel Learning Solver via Deep Neural Networks
In contrast to previous works, as a learning principle we propose {\em parameterizing} both the gating function for learning kernel combination weights and the multiclass classifier in LMKL using an attentional network (AN) and a multilayer perceptron (MLP), respectively.
Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks
By lifting the ReLU function into a higher dimensional space, we develop a smooth multi-convex formulation for training feed-forward deep neural networks (DNNs).
BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning
Understanding the global optimality in deep learning (DL) has been attracting more and more attention recently.
Sequential Optimization for Efficient High-Quality Object Proposal Generation
We propose a novel object proposal algorithm, BING++, which inherits the virtue of good computational efficiency of BING but significantly improves its proposal localization quality.
Learning Joint Feature Adaptation for Zero-Shot Recognition
In this paper we propose a novel framework of learning data-dependent feature transforms for scoring similarity between an arbitrary pair of source and target data instances to account for the wide variability in target domain.
Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter Learning
By exploiting the anisotropy of the filter response, three sparsity related loss functions are proposed to alleviate the overfitting issue of previous methods and improve the overall tracking performance.
Zero-Shot Learning via Joint Latent Similarity Embedding
It takes an arbitrary pair of source and target domain instances as input and predicts whether or not they come from the same class, i. e. whether there is a match.
Efficient Training of Very Deep Neural Networks for Supervised Hashing
In this paper, we propose training very deep neural networks (DNNs) for supervised learning of hash codes.
Zero-Shot Learning via Semantic Similarity Embedding
In this paper we consider a version of the zero-shot learning problem where seen class source and target domain data are provided.
Group Membership Prediction
In this context we propose a novel probability model and introduce latent {\em view-specific} and {\em view-shared} random variables to jointly account for the view-specific appearance and cross-view similarities among data instances.
PRISM: Person Re-Identification via Structured Matching
From a visual perspective re-id is challenging due to significant changes in visual appearance of individuals in cameras with different pose, illumination and calibration.
A Novel Visual Word Co-occurrence Model for Person Re-identification
We first map each pixel of an image to a visual word using a codebook, which is learned in an unsupervised manner.
Object Proposal Generation using Two-Stage Cascade SVMs
Specifically, we explain our scale/aspect-ratio quantization scheme, and investigate the effects of combinations of $\ell_1$ and $\ell_2$ regularizers in cascade SVMs with/without ranking constraints in learning.
RAPID: Rapidly Accelerated Proximal Gradient Algorithms for Convex Minimization
In this paper, we propose a new algorithm to speed-up the convergence of accelerated proximal gradient (APG) methods.
Regularization for Multiple Kernel Learning via Sum-Product Networks
In this paper, we are interested in constructing general graph-based regularizers for multiple kernel learning (MKL) given a structure which is used to describe the way of combining basis kernels.
Learning Anchor Planes for Classification
It provides a set of anchor points which form a local coordinate system, such that each data point on the manifold can be approximated by a linear combination of its anchor points, and the linear weights become the local coordinate coding.
BING: Binarized Normed Gradients for Objectness Estimation at 300fps
Training a generic objectness measure to produce a small set of candidate object windows, has been shown to speed up the classical sliding window object detection paradigm.
Time-Delay Momentum: A Regularization Perspective on the Convergence and Generalization of Stochastic Momentum for Deep Learning
In this paper we study the problem of convergence and generalization error bound of stochastic momentum for deep learning from the perspective of regularization.
Equilibrated Recurrent Neural Network: Neuronal Time-Delayed Self-Feedback Improves Accuracy and Stability
We show that such self-feedback helps stabilize the hidden state transitions leading to fast convergence during training while efficiently learning discriminative latent features that result in state-of-the-art results on several benchmark datasets at test-time.
Verification of Very Low-Resolution Faces Using An Identity-Preserving Deep Face Super-Resolution Network
Face super-resolution methods usually aim at producing visually appealing results rather than preserving distinctive features for further face identification.
RNNs Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients?
Recurrent neural networks (RNNs) are particularly well-suited for modeling long-term dependencies in sequential data, but are notoriously hard to train because the error backpropagated in time either vanishes or explodes at an exponential rate.
Unsupervised Deep Feature Transfer for Low Resolution Image Classification
We use pre-trained convenet to extract features for both high- and low-resolution images, and then feed them into a two-layer feature transfer network for knowledge transfer.
Towards Learning Affine-Invariant Representations via Data-Efficient CNNs
In this paper we propose integrating a priori knowledge into both design and training of convolutional neural networks (CNNs) to learn object representations that are invariant to affine transformations (i. e., translation, scale, rotation).
Graph-Preserving Grid Layout: A Simple Graph Drawing Method for Graph Classification using CNNs
Graph convolutional networks (GCNs) suffer from the irregularity of graphs, while more widely-used convolutional neural networks (CNNs) benefit from regular grids.
Self-Orthogonality Module: A Network Architecture Plug-in for Learning Orthogonal Filters
In this paper, we investigate the empirical impact of orthogonality regularization (OR) in deep learning, either solo or collaboratively.
Automatic Building and Labeling of HD Maps with Deep Learning
This approach speeds up the process of building and labeling HD maps, which can make meaningful contribution to the deployment of autonomous vehicle.
LodoNet: A Deep Neural Network with 2D Keypoint Matchingfor 3D LiDAR Odometry Estimation
Deep learning based LiDAR odometry (LO) estimation attracts increasing research interests in the field of autonomous driving and robotics.
RNN Training along Locally Optimal Trajectories via Frank-Wolfe Algorithm
We propose to utilize the Frank-Wolfe (FW) algorithm in this context.
f-GAIL: Learning f-Divergence for Generative Adversarial Imitation Learning
This naturally gives rise to the following question: Given a set of expert demonstrations, which divergence can recover the expert policy more accurately with higher data efficiency?
EllipsoidNet: Ellipsoid Representation for Point Cloud Classification and Segmentation
In recent years, point cloud representation in 2D space has attracted increasing research interest since it exposes the local geometry features in a 2D space.
Revisiting 2D Convolutional Neural Networks for Graph-based Applications
Graph convolutional networks (GCNs) are widely used in graph-based applications such as graph classification and segmentation.
An Optimization Perspective on Realizing Backdoor Injection Attacks on Deep Neural Networks in Hardware
Recent works focus on software simulation of backdoor injection during the inference phase by modifying network weights, which we find often unrealistic in practice due to the hardware restriction such as bit allocation in memory.
Stabilized Likelihood-based Imitation Learning via Denoising Continuous Normalizing Flow
State-of-the-art imitation learning (IL) approaches, e. g, GAIL, apply adversarial training to minimize the discrepancy between expert and learner behaviors, which is prone to unstable training and mode collapse.
Auto-Encoding Inverse Reinforcement Learning
Reinforcement learning (RL) provides a powerful framework for decision-making, but its application in practice often requires a carefully designed reward function.
Learning Lightweight Neural Networks via Channel-Split Recurrent Convolution
Lightweight neural networks refer to deep networks with small numbers of parameters, which are allowed to be implemented in resource-limited hardware such as embedded systems.
CoFi: Coarse-to-Fine ICP for LiDAR Localization in an Efficient Long-lasting Point Cloud Map
In addition, we propose a map based LiDAR localization algorithm that extracts semantic feature points from the LiDAR frames and apply CoFi to estimate the pose on an efficient point cloud map.
SBO-RNN: Reformulating Recurrent Neural Networks via Stochastic Bilevel Optimization
In this paper we consider the training stability of recurrent neural networks (RNNs) and propose a family of RNNs, namely SBO-RNN, that can be formulated using stochastic bilevel optimization (SBO).
Auto-Encoding Adversarial Imitation Learning
In this work, we propose Auto-Encoding Adversarial Imitation Learning (AEAIL), a robust and scalable AIL framework.
EgoSpeed-Net: Forecasting Speed-Control in Driver Behavior from Egocentric Video Data
Speed-control forecasting, a challenging problem in driver behavior analysis, aims to predict the future actions of a driver in controlling vehicle speed such as braking or acceleration.
Simultaneous Estimation of Hand Configurations and Finger Joint Angles using Forearm Ultrasound
Hand configuration classification and MCP joint angle detection is important for a comprehensive reconstruction of hand motion.
Hyperbolic Contrastive Learning
Learning good image representations that are beneficial to downstream tasks is a challenging task in computer vision.
PRISE: Demystifying Deep Lucas-Kanade with Strongly Star-Convex Constraints for Multimodel Image Alignment
The Lucas-Kanade (LK) method is a classic iterative homography estimation algorithm for image alignment, but often suffers from poor local optimality especially when image pairs have large distortions.
Hyperbolic Chamfer Distance for Point Cloud Completion
Chamfer distance (CD) is a standard metric to measure the shape dissimilarity between point clouds in point cloud completion, as well as a loss function for (deep) learning.
Understanding Hyperbolic Metric Learning through Hard Negative Sampling
In recent years, there has been a growing trend of incorporating hyperbolic geometry methods into computer vision.
