Search Results for author: Guanghui Wang

Found 62 papers, 10 papers with code

Dynamic Label Assignment for Object Detection by Combining Predicted and Anchor IoUs

no code implementations23 Jan 2022 Tianxiao Zhang, Ajay Sharda, Bo Luo, Guanghui Wang

For anchor-based detection models, the IoU threshold between the anchors and their corresponding ground truth bounding boxes is the key element since the positive samples and negative samples are divided by the IoU threshold.

Object Detection

An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training

no code implementations31 Dec 2021 Yiju Yang, Tianxiao Zhang, Guanyu Li, Taejoon Kim, Guanghui Wang

In this paper, we propose a dual-module network architecture that employs a domain discriminative feature module to encourage the domain invariant feature module to learn more domain invariant features.

Unsupervised Domain Adaptation

Miti-DETR: Object Detection based on Transformers with Mitigatory Self-Attention Convergence

1 code implementation26 Dec 2021 Wenchi Ma, Tianxiao Zhang, Guanghui Wang

Object Detection with Transformers (DETR) and related works reach or even surpass the highly-optimized Faster-RCNN baseline with self-attention network architectures.

Object Detection

Semantic Clustering based Deduction Learning for Image Recognition and Classification

no code implementations25 Dec 2021 Wenchi Ma, Xuemin Tu, Bo Luo, Guanghui Wang

The paper proposes a semantic clustering based deduction learning by mimicking the learning and thinking process of human brains.

Towards More Effective PRM-based Crowd Counting via A Multi-resolution Fusion and Attention Network

no code implementations17 Dec 2021 Usman Sajid, Guanghui Wang

The paper focuses on improving the recent plug-and-play patch rescaling module (PRM) based approaches for crowd counting.

Crowd Counting

A Discriminative Channel Diversification Network for Image Classification

1 code implementation10 Dec 2021 Krushi Patel, Guanghui Wang

Channel attention mechanisms in convolutional neural networks have been proven to be effective in various computer vision tasks.

Image Classification

A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translation

no code implementations21 Oct 2021 Wenju Xu, Guanghui Wang

Existing approaches rely on a cycle-consistency constraint that supervises the generators to learn an inverse mapping.

Image-to-Image Translation Translation

DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer

no code implementations ICCV 2021 Wenju Xu, Chengjiang Long, Ruisheng Wang, Guanghui Wang

The style code is modeled as the shared parameters for Dynamic ResBlocks connecting both the style encoding network and the style transfer network.

Style Transfer

Momentum Accelerates the Convergence of Stochastic AUPRC Maximization

no code implementations2 Jul 2021 Guanghui Wang, Ming Yang, Lijun Zhang, Tianbao Yang

In this paper, we study stochastic optimization of areas under precision-recall curves (AUPRC), which is widely used for combating imbalanced classification tasks.

imbalanced classification Stochastic Optimization

A Fine-Grained Visual Attention Approach for Fingerspelling Recognition in the Wild

no code implementations17 May 2021 Kamala Gajurel, Cuncong Zhong, Guanghui Wang

The fine-grained attention is achieved by utilizing the change in motion of the video frames (optical flow) in sequential context-based attention along with a Transformer encoder model.

Optical Flow Estimation

Few-Shot Learning by Integrating Spatial and Frequency Representation

1 code implementation11 May 2021 Xiangyu Chen, Guanghui Wang

We employ Discrete Cosine Transformation (DCT) to generate the frequency representation, then, integrate the features from both the spatial domain and frequency domain for classification.

Few-Shot Image Classification

A Simple yet Universal Strategy for Online Convex Optimization

no code implementations8 May 2021 Lijun Zhang, Guanghui Wang, JinFeng Yi, Tianbao Yang

In this paper, we propose a simple strategy for universal online convex optimization, which avoids these limitations.

Enhanced U-Net: A Feature Enhancement Network for Polyp Segmentation

1 code implementation3 May 2021 Krushi Patel, Andres M. Bur, Guanghui Wang

Colonoscopy is a procedure to detect colorectal polyps which are the primary cause for developing colorectal cancer.

Parallel Scale-wise Attention Network for Effective Scene Text Recognition

no code implementations25 Apr 2021 Usman Sajid, Michael Chow, Jin Zhang, Taejoon Kim, Guanghui Wang

To address these issues, we propose a new multi-scale and encoder-based attention network for text recognition that performs the multi-scale FE and VA in parallel.

Scene Text Recognition

Training Deep Neural Networks via Branch-and-Bound

1 code implementation5 Apr 2021 Yuanwei Wu, Ziming Zhang, Guanghui Wang

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.

Object Recognition Stochastic Optimization

Online Convex Optimization with Continuous Switching Constraint

no code implementations NeurIPS 2021 Guanghui Wang, Yuanyu Wan, Tianbao Yang, Lijun Zhang

To control the switching cost, we introduce the problem of online convex optimization with continuous switching constraint, where the goal is to achieve a small regret given a budget on the \emph{overall} switching cost.

Decision Making

Projection-free Distributed Online Learning with Strongly Convex Losses

no code implementations20 Mar 2021 Yuanyu Wan, Guanghui Wang, Lijun Zhang

Specifically, we first propose a distributed projection-free algorithm for strongly convex loss functions, which enjoys a better regret bound of $O(T^{2/3}\log T)$ with smaller communication complexity of $O(T^{1/3})$.

Classification of Long Noncoding RNA Elements Using Deep Convolutional Neural Networks and Siamese Networks

no code implementations10 Feb 2021 Brian McClannahan, Cucong Zhong, Guanghui Wang

To this end, this paper first proposes anefficient approach to convert the RNA sequences into imagescharacterizing their base-pairing probability.

General Classification

SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images

no code implementations19 Jan 2021 Lei He, Jiwen Lu, Guanghui Wang, Shiyu Song, Jie zhou

In this paper, we first introduce the concept of semantic objectness to exploit the geometric relationship of these two tasks through an analysis of the imaging process, then propose a Semantic Object Segmentation and Depth Estimation Network (SOSD-Net) based on the objectness assumption.

Monocular Depth Estimation Multi-Task Learning +2

Six-channel Image Representation for Cross-domain Object Detection

no code implementations3 Jan 2021 Tianxiao Zhang, Wenchi Ma, Guanghui Wang

If we train the detector using the data from one domain, it cannot perform well on the data from another domain due to domain shift, which is one of the big challenges of most object detection models.

Object Detection Translation +1

Efficient Golf Ball Detection and Tracking Based on Convolutional Neural Networks and Kalman Filter

1 code implementation17 Dec 2020 Tianxiao Zhang, Xiaohan Zhang, Yiju Yang, Zongbo Wang, Guanghui Wang

The detection is performed on small image patches instead of the entire image to increase the performance of small ball detection.

Object Detection

Deep Feature Augmentation for Occluded Image Classification

no code implementations2 Nov 2020 Feng Cen, Xiaoyu Zhao, Wuzhuang Li, Guanghui Wang

To alleviate the dependency on large-scale occluded image datasets, we propose a novel approach to improve the classification accuracy of occluded images by fine-tuning the pre-trained models with a set of augmented deep feature vectors (DFVs).

General Classification Image Classification

Stereo Frustums: A Siamese Pipeline for 3D Object Detection

no code implementations27 Oct 2020 Xi Mo, Usman Sajid, Guanghui Wang

The paper proposes a light-weighted stereo frustums matching module for 3D objection detection.

3D Object Detection Autonomous Driving +2

Why Layer-Wise Learning is Hard to Scale-up and a Possible Solution via Accelerated Downsampling

no code implementations15 Oct 2020 Wenchi Ma, Miao Yu, Kaidong Li, Guanghui Wang

This paper, for the first time, reveals the fundamental reason that impedes the scale-up of layer-wise learning is due to the relatively poor separability of the feature space in shallow layers.

Image Classification

Multi-Resolution Fusion and Multi-scale Input Priors Based Crowd Counting

no code implementations4 Oct 2020 Usman Sajid, Wenchi Ma, Guanghui Wang

The state-of-the-art patch rescaling module (PRM) based approaches prove to be very effective in improving the crowd counting performance.

Crowd Counting

Location-Aware Box Reasoning for Anchor-Based Single-Shot Object Detection

no code implementations13 Jul 2020 Wenchi Ma, Kaidong Li, Guanghui Wang

In this paper, we aim at single-shot object detectors and propose a location-aware anchor-based reasoning (LAAR) for the bounding boxes.

General Classification Object Detection +1

A Comparative Study on Polyp Classification using Convolutional Neural Networks

no code implementations12 Jul 2020 Krushi Patel, Kaidong Li, Ke Tao, Quan Wang, Ajay Bansal, Amit Rastogi, Guanghui Wang

In this work, we compare the performance of the state-of-the-art general object classification models for polyp classification.

General Classification

Nearly Optimal Regret for Stochastic Linear Bandits with Heavy-Tailed Payoffs

no code implementations28 Apr 2020 Bo Xue, Guanghui Wang, Yimu Wang, Lijun Zhang

In this paper, we study the problem of stochastic linear bandits with finite action sets.

ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images

no code implementations27 Feb 2020 Usman Sajid, Hasan Sajid, Hongcheng Wang, Guanghui Wang

This module also provides a count for each label, which is then analyzed via a specifically devised novel decision module to decide whether the image belongs to any of the two extreme cases (very low or very high density) or a normal case.

Crowd Counting

Boosting Occluded Image Classification via Subspace Decomposition Based Estimation of Deep Features

1 code implementation13 Jan 2020 Feng Cen, Guanghui Wang

By employing the ResNet-152, pre-trained on the ILSVRC2012 training set, as the base network, the proposed SBDE-based classification scheme is extensively evaluated on the Caltech-101 and ILSVRC2012 datasets.

General Classification Image Classification

Plug-and-Play Rescaling Based Crowd Counting in Static Images

no code implementations6 Jan 2020 Usman Sajid, Guanghui Wang

Crowd counting is a challenging problem especially in the presence of huge crowd diversity across images and complex cluttered crowd-like background regions, where most previous approaches do not generalize well and consequently produce either huge crowd underestimation or overestimation.

Crowd Counting

Self-Orthogonality Module: A Network Architecture Plug-in for Learning Orthogonal Filters

no code implementations5 Jan 2020 Ziming Zhang, Wenchi Ma, Yuanwei Wu, Guanghui Wang

In this paper, we investigate the empirical impact of orthogonality regularization (OR) in deep learning, either solo or collaboratively.

MDFN: Multi-Scale Deep Feature Learning Network for Object Detection

no code implementations10 Dec 2019 Wenchi Ma, Yuanwei Wu, Feng Cen, Guanghui Wang

Compared with features produced in earlier layers, the deep features are better at expressing semantic and contextual information.

Object Detection

Object Detection with Convolutional Neural Networks

no code implementations4 Dec 2019 Kaidong Li, Wenchi Ma, Usman Sajid, Yuanwei Wu, Guanghui Wang

In this chapter, we present a brief overview of the recent development in object detection using convolutional neural networks (CNN).

Object Detection

Direct Visual-Inertial Odometry with Semi-Dense Mapping

no code implementations4 Oct 2019 Wenju Xu, Dongkyu Choi, Guanghui Wang

The first one, based on Direct Sparse Odometry (DSO), is to estimate the depths of candidate points for mapping and dense visual tracking.

Visual Odometry Visual Tracking

Adaptively Denoising Proposal Collection forWeakly Supervised Object Localization

no code implementations arXiv 2019 Wenju Xu, Yuanwei Wu, Wenchi Ma, Guanghui Wang

In this paper, we address the problem of weakly supervisedobject localization (WSL), which trains a detection network on the datasetwith only image-level annotations.

Denoising Multiple Instance Learning +2

Stacked Wasserstein Autoencoder

no code implementations4 Oct 2019 Wenju Xu, Shawn Keshmiri, Guanghui Wang

At the first stage, the SWAE flexibly learns a representation distribution, i. e., the encoded prior; and at the second stage, the encoded representation distribution is approximated with a latent variable model under the regularization encouraging the latent distribution to match the explicit prior.

Representation Learning

Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization

no code implementations4 Oct 2019 Wenju Xu, Yuanwei Wu, Wenchi Ma, Guanghui Wang

In this paper, we address the problem of weakly supervised object localization (WSL), which trains a detection network on the dataset with only image-level annotations.

Denoising Multiple Instance Learning +1

Towards Learning Affine-Invariant Representations via Data-Efficient CNNs

no code implementations31 Aug 2019 Xenju Xu, Guanghui Wang, Alan Sullivan, Ziming Zhang

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).


Unsupervised Deep Feature Transfer for Low Resolution Image Classification

no code implementations27 Aug 2019 Yuanwei Wu, Ziming Zhang, Guanghui Wang

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.

General Classification Image Classification +1

Bandit Convex Optimization in Non-stationary Environments

no code implementations29 Jul 2019 Peng Zhao, Guanghui Wang, Lijun Zhang, Zhi-Hua Zhou

In this paper, we investigate BCO in non-stationary environments and choose the \emph{dynamic regret} as the performance measure, which is defined as the difference between the cumulative loss incurred by the algorithm and that of any feasible comparator sequence.

Decision Making

Dual Adaptivity: A Universal Algorithm for Minimizing the Adaptive Regret of Convex Functions

no code implementations NeurIPS 2021 Lijun Zhang, Guanghui Wang, Wei-Wei Tu, Zhi-Hua Zhou

Along this line of research, this paper presents the first universal algorithm for minimizing the adaptive regret of convex functions.

Multi-Objective Generalized Linear Bandits

no code implementations30 May 2019 Shiyin Lu, Guanghui Wang, Yao Hu, Lijun Zhang

In this paper, we study the multi-objective bandits (MOB) problem, where a learner repeatedly selects one arm to play and then receives a reward vector consisting of multiple objectives.

Multi-Armed Bandits

Toward Learning a Unified Many-to-Many Mapping for Diverse Image Translation

no code implementations21 May 2019 Wenju Xu, Shawn Keshmiri, Guanghui Wang

Image-to-image translation, which translates input images to a different domain with a learned one-to-one mapping, has achieved impressive success in recent years.

Image-to-Image Translation Translation

Adaptivity and Optimality: A Universal Algorithm for Online Convex Optimization

no code implementations15 May 2019 Guanghui Wang, Shiyin Lu, Lijun Zhang

In this paper, we study adaptive online convex optimization, and aim to design a universal algorithm that achieves optimal regret bounds for multiple common types of loss functions.

SAdam: A Variant of Adam for Strongly Convex Functions

1 code implementation ICLR 2020 Guanghui Wang, Shiyin Lu, Wei-Wei Tu, Lijun Zhang

In this paper, we give an affirmative answer by developing a variant of Adam (referred to as SAdam) which achieves a data-dependant $O(\log T)$ regret bound for strongly convex functions.

Adversarially Approximated Autoencoder for Image Generation and Manipulation

no code implementations14 Feb 2019 Wenju Xu, Shawn Keshmiri, Guanghui Wang

Regularized autoencoders learn the latent codes, a structure with the regularization under the distribution, which enables them the capability to infer the latent codes given observations and generate new samples given the codes.

Image Generation

MDCN: Multi-Scale, Deep Inception Convolutional Neural Networks for Efficient Object Detection

no code implementations6 Sep 2018 Wenchi Ma, Yuanwei Wu, Zongbo Wang, Guanghui Wang

To better handle these challenges, the paper proposes a novel framework, multi-scale, deep inception convolutional neural network (MDCN), which focuses on wider and broader object regions by activating feature maps produced in the deep part of the network.

Object Detection

An Efficient Approach for Polyps Detection in Endoscopic Videos Based on Faster R-CNN

no code implementations4 Sep 2018 Xi Mo, Ke Tao, Quan Wang, Guanghui Wang

Polyp has long been considered as one of the major etiologies to colorectal cancer which is a fatal disease around the world, thus early detection and recognition of polyps plays a crucial role in clinical routines.

Learning Depth from Single Images with Deep Neural Network Embedding Focal Length

no code implementations27 Mar 2018 Lei He, Guanghui Wang, Zhanyi Hu

In order to learn monocular depth by embedding the focal length, we propose a method to generate synthetic varying-focal-length dataset from fixed-focal-length datasets, and a simple and effective method is implemented to fill the holes in the newly generated images.

Depth Estimation Network Embedding +1

BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning

no code implementations CVPR 2018 Ziming Zhang, Yuanwei Wu, Guanghui Wang

Understanding the global optimality in deep learning (DL) has been attracting more and more attention recently.

Object Recognition

Vision-based Real-Time Aerial Object Localization and Tracking for UAV Sensing System

no code implementations19 Mar 2017 Yuanwei Wu, Yao Sui, Guanghui Wang

The paper focuses on the problem of vision-based obstacle detection and tracking for unmanned aerial vehicle navigation.

Object Detection Object Localization

Robust Structure from Motion in the Presence of Outliers and Missing Data

no code implementations9 Sep 2016 Guanghui Wang

In this paper, the state-of-the-art techniques for structure and motion factorization of non-rigid objects are reviewed and discussed.

Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter Learning

no code implementations29 Aug 2016 Yao Sui, Ziming Zhang, Guanghui Wang, Yafei Tang, Li Zhang

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.

Real-Time Visual Tracking

Tracking Completion

no code implementations29 Aug 2016 Yao Sui, Guanghui Wang, Yafei Tang, Li Zhang

A fundamental component of modern trackers is an online learned tracking model, which is typically modeled either globally or locally.

Matrix Completion

A Novel Feature Extraction Method for Scene Recognition Based on Centered Convolutional Restricted Boltzmann Machines

no code implementations24 Jun 2015 Jingyu Gao, Jinfu Yang, Guanghui Wang, Mingai Li

In this paper, a novel feature extraction method, named Centered Convolutional Restricted Boltzmann Machines (CCRBM), is proposed for scene recognition.

Object Recognition Scene Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.