no code implementations • 12 Feb 2025 • Guanghui Wang, Krishna Acharya, Lokranjan Lakshmikanthan, Vidya Muthukumar, Juba Ziani
Our analysis characterizes the equilibria of this game and demonstrates that when both firms use a common and natural no-regret learning dynamic -- exponential weights -- with proper initialization, the dynamics always converge to stable outcomes despite the general-sum structure.
no code implementations • 11 Feb 2025 • Fady Ibrahim, Guangjun Liu, Guanghui Wang
Transformers have become foundational for visual tasks such as object detection, semantic segmentation, and video understanding, but their quadratic complexity in attention mechanisms presents scalability challenges.
no code implementations • 26 Jan 2025 • Milad Khademi Nori, Il-Min Kim, Guanghui Wang
Meanwhile, at the clients, the decoder decodes the stored low-dimensional latent space exemplars back to the high-dimensional input space, used to address local forgetting.
1 code implementation • 7 Jan 2025 • Xiaojiao Xiao, Qinmin Vivian Hu, Guanghui Wang
Multi-modality magnetic resonance imaging (MRI) is essential for the diagnosis and treatment of brain tumors.
no code implementations • 18 Oct 2024 • Tianxiao Zhang, Bo Luo, Guanghui Wang
Vision Transformers have made remarkable progress in recent years, achieving state-of-the-art performance in most vision tasks.
no code implementations • 15 Oct 2024 • Longlong Li, YiPeng Zhang, Guanghui Wang, Kelin Xia
This work not only highlights the great power of KA-GNNs in molecular property prediction but also provides a novel geometric deep learning framework for the general non-Euclidean data analysis.
1 code implementation • 13 Oct 2024 • Kaidong Li, Tianxiao Zhang, Cuncong Zhong, Ziming Zhang, Guanghui Wang
The generative model-based mapping algorithms yield regular 2D images, further minimizing the domain gap from regular 2D classification tasks.
no code implementations • 13 Oct 2024 • Gangtao Han, Chunxiao Song, Song Wang, Hao Wang, Enqing Chen, Guanghui Wang
In this paper, we propose an occluded human pose estimation framework based on limb joint augmentation to enhance the generalization ability of the pose estimation model on the occluded human bodies.
1 code implementation • 9 Oct 2024 • Wentao Chao, Fuqing Duan, Yulan Guo, Guanghui Wang
Extensive experiments demonstrate the efficacy of MaskBlur in significantly enhancing the performance of existing SR methods.
1 code implementation • 28 Jul 2024 • Tianxiao Zhang, Wenju Xu, Bo Luo, Guanghui Wang
The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks.
1 code implementation • 17 Jun 2024 • Song Wang, Zhong Zhang, Huan Yan, Ming Xu, Guanghui Wang
H&E-to-IHC stain translation techniques offer a promising solution for precise cancer diagnosis, especially in low-resource regions where there is a shortage of health professionals and limited access to expensive equipment.
no code implementations • 22 May 2024 • Guanghui Wang, Dexi Liu, Jian-Yun Nie, Qizhi Wan, Rong Hu, Xiping Liu, Wanlong Liu, Jiaming Liu
In this work, we propose DEGAP to address these challenges through a simple yet effective components: dual prefixes, i. e. learnable prompt vectors, where the instance-oriented prefix and template-oriented prefix are trained to learn information from different event instances and templates.
no code implementations • 7 May 2024 • Raiyan Rahman, Christopher Indris, Goetz Bramesfeld, Tianxiao Zhang, Kaidong Li, Xiangyu Chen, Ivan Grijalva, Brian McCornack, Daniel Flippo, Ajay Sharda, Guanghui Wang
In this study, we trained and evaluated four real-time semantic segmentation models and three object detection models specifically for aphid cluster segmentation and detection.
no code implementations • 14 Apr 2024 • Yufu Wang, Mingwei Zhu, Jiaqiang Yuan, Guanghui Wang, Hong Zhou
Cloud computing (cloud computing) is a kind of distributed computing, referring to the network "cloud" will be a huge data calculation and processing program into countless small programs, and then, through the system composed of multiple servers to process and analyze these small programs to get the results and return to the user.
1 code implementation • 27 Mar 2024 • Krushi Patel, Fengjun Li, Guanghui Wang
Detecting and segmenting polyps is crucial for expediting the diagnosis of colon cancer.
no code implementations • 18 Mar 2024 • Xiangyu Chen, Jing Liu, Ye Wang, Pu, Wang, Matthew Brand, Guanghui Wang, Toshiaki Koike-Akino
Low-rank adaptation (LoRA) and its variants are widely employed in fine-tuning large models, including large language models for natural language processing and diffusion models for computer vision.
no code implementations • 1 Feb 2024 • Mohsena Chowdhury, Tejas Vyas, Rahul Alapati, Andrés M Bur, Guanghui Wang
The results demonstrate the potential of employing machine learning and deep learning techniques to determine a patient's eligibility for Inspire therapy, paving the way for future advancements in this field.
no code implementations • 26 Jan 2024 • Raiyan Rahman, Mohsena Chowdhury, Yueyang Tang, Huayi Gao, George Yin, Guanghui Wang
The escalating global concern over extensive food wastage necessitates innovative solutions to foster a net-zero lifestyle and reduce emissions.
no code implementations • 24 Jan 2024 • Tejas Vyas, Mohsena Chowdhury, Xiaojiao Xiao, Mathias Claeys, Géraldine Ong, Guanghui Wang
Mitral Transcatheter Edge-to-Edge Repair (mTEER) is a medical procedure utilized for the treatment of mitral valve disorders.
no code implementations • 10 Dec 2023 • Wenju Xu, Chengjiang Long, Yongwei Nie, Guanghui Wang
Unlike the existing works leveraging the semantic masks to obtain the representation of each component, we propose to generate disentangled latent code via a novel attribute encoder with transformers trained in a manner of curriculum learning from a relatively easy step to a gradually hard one.
1 code implementation • 27 Nov 2023 • Wentao Chao, Fuqing Duan, Xuechun Wang, Yingqian Wang, Guanghui Wang
Despite this complexity, mainstream LF image SR methods typically adopt a deterministic approach, generating only a single output supervised by pixel-wise loss functions.
no code implementations • 25 Sep 2023 • Zihao Hu, Guanghui Wang, Xi Wang, Andre Wibisono, Jacob Abernethy, Molei Tao
In the context of Euclidean space, it is established that the last-iterates of both the extragradient (EG) and past extragradient (PEG) methods converge to the solution of monotone variational inequality problems at a rate of $O\left(\frac{1}{\sqrt{T}}\right)$ (Cai et al., 2022).
1 code implementation • 24 Aug 2023 • Xiangyu Chen, Ruiwen Zhen, Shuai Li, Xiaotian Li, Guanghui Wang
Extensive experiments demonstrate that our approach decreases runtime by up to 13% and reduces the number of parameters by up to 23%, while increasing PSNR and SSIM on several image restoration datasets.
no code implementations • 10 Aug 2023 • Tianxiao Zhang, Kaidong Li, Xiangyu Chen, Cuncong Zhong, Bo Luo, Ivan Grijalva, Brian McCornack, Daniel Flippo, Ajay Sharda, Guanghui Wang
To facilitate the use of machine learning models, we further process the images by cropping them into patches, resulting in a labeled dataset comprising 151, 380 image patches.
no code implementations • 17 Jul 2023 • Raiyan Rahman, Christopher Indris, Tianxiao Zhang, Kaidong Li, Brian McCornack, Daniel Flippo, Ajay Sharda, Guanghui Wang
We have collected and labeled a large aphid image dataset in the field, and propose the use of real-time semantic segmentation models to segment clusters of aphids.
no code implementations • 12 Jul 2023 • Tianxiao Zhang, Kaidong Li, Xiangyu Chen, Cuncong Zhong, Bo Luo, Ivan Grijalva Teran, Brian McCornack, Daniel Flippo, Ajay Sharda, Guanghui Wang
Aphids are one of the main threats to crops, rural families, and global food security.
no code implementations • 4 Jul 2023 • Xiaojiao Xiao, Qinmin Hu, Guanghui Wang
Simultaneous multi-index quantification, segmentation, and uncertainty estimation of liver tumors on multi-modality non-contrast magnetic resonance imaging (NCMRI) are crucial for accurate diagnosis.
no code implementations • NeurIPS 2023 • Zihao Hu, Guanghui Wang, Jacob Abernethy
The projection operation is a critical component in a wide range of optimization algorithms, such as online gradient descent (OGD), for enforcing constraints and achieving optimal regret bounds.
1 code implementation • 28 May 2023 • Wentao Chao, Fuqing Duan, Xuechun Wang, Yingqian Wang, Guanghui Wang
To address this issue and achieve a better trade-off between accuracy and efficiency, we propose an occlusion-aware cascade cost volume for LF depth (disparity) estimation.
no code implementations • NeurIPS 2023 • Guanghui Wang, Zihao Hu, Claudio Gentile, Vidya Muthukumar, Jacob Abernethy
To address this limitation, we present a series of state-of-the-art implicit bias rates for mirror descent and steepest descent algorithms.
no code implementations • 26 May 2023 • Tianxiao Zhang, Andrés M. Bur, Shannon Kraft, Hannah Kavookjian, Bryan Renslo, Xiangyu Chen, Bo Luo, Guanghui Wang
In this study, we made the first endeavor to employ deep learning models to predict patient demographic information to improve detector model performance.
no code implementations • 17 Feb 2023 • Zihao Hu, Guanghui Wang, Jacob Abernethy
In this paper, we consider the sequential decision problem where the goal is to minimize the general dynamic regret on a complete Riemannian manifold.
1 code implementation • 25 Oct 2022 • Xiangyu Chen, Ying Qin, Wenju Xu, Andrés M. Bur, Cuncong Zhong, Guanghui Wang
To boost the performance of vision Transformers on small datasets, this paper proposes to explicitly increase the input information density in the frequency domain.
1 code implementation • 22 Oct 2022 • Xiangyu Chen, Qinghao Hu, Kaidong Li, Cuncong Zhong, Guanghui Wang
After carefully examining the self-attention modules, we discover that the number of trivial attention weights is far greater than the important ones and the accumulated trivial weights are dominating the attention in Vision Transformers due to their large quantity, which is not handled by the attention itself.
no code implementations • 17 Oct 2022 • Guanghui Wang, Zihao Hu, Vidya Muthukumar, Jacob Abernethy
The classical algorithms for online learning and decision-making have the benefit of achieving the optimal performance guarantees, but suffer from computational complexity limitations when implemented at scale.
no code implementations • 17 Oct 2022 • Guanghui Wang, Rafael Hanashiro, Etash Guha, Jacob Abernethy
The classical Perceptron algorithm of Rosenblatt can be used to find a linear threshold function to correctly classify $n$ linearly separable data points, assuming the classes are separated by some margin $\gamma > 0$.
2 code implementations • 20 Aug 2022 • Wentao Chao, Xuechun Wang, Yingqian Wang, Guanghui Wang, Fuqing Duan
However, the disparity map is only a sub-space projection (i. e., an expectation) of the disparity distribution, which is essential for models to learn.
no code implementations • 17 Apr 2022 • Yao Sui, Guanghui Wang, Li Zhang
The paper focuses on a classical tracking model, subspace learning, grounded on the fact that the targets in successive frames are considered to reside in a low-dimensional subspace or manifold due to the similarity in their appearances.
1 code implementation • CVPR 2022 • Kaidong Li, Ziming Zhang, Cuncong Zhong, Guanghui Wang
Deep neural networks for 3D point cloud classification, such as PointNet, have been demonstrated to be vulnerable to adversarial attacks.
1 code implementation • 30 Jan 2022 • Krushi Patel, Andres M. Bur, Fengjun Li, Guanghui Wang
Local Transformer-based classification models have recently achieved promising results with relatively low computational costs.
1 code implementation • 23 Jan 2022 • Tianxiao Zhang, Bo Luo, Ajay Sharda, Guanghui Wang
For anchor-based detection models, the IoU (Intersection over Union) 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.
no code implementations • 31 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.
1 code implementation • 26 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.
no code implementations • 25 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.
no code implementations • 17 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.
1 code implementation • 10 Dec 2021 • Krushi Patel, Guanghui Wang
Channel attention mechanisms in convolutional neural networks have been proven to be effective in various computer vision tasks.
no code implementations • 21 Oct 2021 • Wenju Xu, Guanghui Wang
Existing approaches rely on a cycle-consistency constraint that supervises the generators to learn an inverse mapping.
Generative Adversarial Network
Image-to-Image Translation
+1
no code implementations • 4 Sep 2021 • Usman Sajid, Xiangyu Chen, Hasan Sajid, Taejoon Kim, Guanghui Wang
Crowd estimation is a very challenging problem.
1 code implementation • 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.
1 code implementation • 2 Aug 2021 • Yiju Yang, Taejoon Kim, Guanghui Wang
In this paper, we propose to extend the structure to multiple classifiers to further boost its performance.
no code implementations • 2 Jul 2021 • Guanghui Wang, Ming Yang, Lijun Zhang, Tianbao Yang
In this paper, we further improve the stochastic optimization of AURPC by (i) developing novel stochastic momentum methods with a better iteration complexity of $O(1/\epsilon^4)$ for finding an $\epsilon$-stationary solution; and (ii) designing a novel family of stochastic adaptive methods with the same iteration complexity, which enjoy faster convergence in practice.
no code implementations • 17 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.
1 code implementation • 11 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.
no code implementations • 8 May 2021 • Lijun Zhang, Yibo Wang, Guanghui Wang, JinFeng Yi, Tianbao Yang
In this paper, we propose a simple strategy for universal online convex optimization, which avoids these limitations.
1 code implementation • 3 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.
1 code implementation • 26 Apr 2021 • Kaidong Li, Nina Y. Wang, Yiju Yang, Guanghui Wang
A super-class branch (SCB), trained on super-class labels, is introduced to guide finer class prediction.
no code implementations • 25 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.
no code implementations • 22 Apr 2021 • Kaidong Li, Mohammad I. Fathan, Krushi Patel, Tianxiao Zhang, Cuncong Zhong, Ajay Bansal, Amit Rastogi, Jean S. Wang, Guanghui Wang
This work can serve as a baseline for future research in polyp detection and classification.
1 code implementation • 5 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.
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.
no code implementations • 20 Mar 2021 • Yuanyu Wan, Guanghui Wang, Wei-Wei Tu, Lijun Zhang
In this paper, we propose an improved variant of D-OCG, namely D-BOCG, which can attain the same $O(T^{3/4})$ regret bound with only $O(\sqrt{T})$ communication rounds for convex losses, and a better regret bound of $O(T^{2/3}(\log T)^{1/3})$ with fewer $O(T^{1/3}(\log T)^{2/3})$ communication rounds for strongly convex losses.
no code implementations • 10 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.
no code implementations • 19 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.
Ranked #88 on
Semantic Segmentation
on NYU Depth v2
no code implementations • 3 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.
1 code implementation • 17 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.
no code implementations • 2 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).
no code implementations • 27 Oct 2020 • Xi Mo, Usman Sajid, Guanghui Wang
The paper proposes a light-weighted stereo frustums matching module for 3D objection detection.
no code implementations • 15 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.
no code implementations • 4 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.
no code implementations • 24 Aug 2020 • Brian McClannahan, Krushi Patel, Usman Sajid, Cuncong Zhong, Guanghui Wang
The paper proposes to employ deep convolutional neural networks (CNNs) to classify noncoding RNA (ncRNA) sequences.
no code implementations • 13 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.
no code implementations • 12 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.
no code implementations • 28 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.
no code implementations • 27 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.
1 code implementation • 13 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.
no code implementations • 6 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.
no code implementations • 5 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.
no code implementations • 10 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.
no code implementations • 4 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).
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.
no code implementations • 4 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.
no code implementations • 4 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.
no code implementations • 4 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.
no code implementations • 31 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).
no code implementations • 27 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.
no code implementations • 29 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.
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.
no code implementations • 30 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.
no code implementations • 21 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.
no code implementations • 15 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.
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.
no code implementations • 14 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.
no code implementations • 6 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.
no code implementations • 4 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.
no code implementations • 27 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.
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.
no code implementations • 19 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.
no code implementations • 9 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.
no code implementations • 29 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.
no code implementations • 29 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.
no code implementations • 24 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.
no code implementations • 24 Jun 2015 • Jinfu Yang, Jingyu Gao, Guanghui Wang, Shanshan Zhang
However, the DBM is limited in scene recognition due to the fact that natural scene images are usually very large.