Search Results for author:
Found 89 papers, 20 papers with code
Aggregating Global Features into Local Vision Transformer
Local Transformer-based classification models have recently achieved promising results with relatively low computational costs.
Efficient Golf Ball Detection and Tracking Based on Convolutional Neural Networks and Kalman Filter
The detection is performed on small image patches instead of the entire image to increase the performance of small ball detection.
DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer
The style code is modeled as the shared parameters for Dynamic ResBlocks connecting both the style encoding network and the style transfer network.
Few-Shot Learning by Integrating Spatial and Frequency Representation
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.
Learning Sub-Pixel Disparity Distribution for Light Field Depth Estimation
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.
Dynamic Label Assignment for Object Detection by Combining Predicted IoUs and Anchor IoUs
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.
Enhanced U-Net: A Feature Enhancement Network for Polyp Segmentation
Colonoscopy is a procedure to detect colorectal polyps which are the primary cause for developing colorectal cancer.
MOFA: A Model Simplification Roadmap for Image Restoration on Mobile Devices
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.
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.
Accumulated Trivial Attention Matters in Vision Transformers on Small Datasets
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.
OccCasNet: Occlusion-aware Cascade Cost Volume for Light Field Depth Estimation
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.
LFSRDiff: Light Field Image Super-Resolution via Diffusion Models
Despite this complexity, mainstream LF image SR methods typically adopt a deterministic approach, generating only a single output supervised by pixel-wise loss functions.
SGNet: A Super-class Guided Network for Image Classification and Object Detection
A super-class branch (SCB), trained on super-class labels, is introduced to guide finer class prediction.
Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
In this paper, we propose to extend the structure to multiple classifiers to further boost its performance.
Explicitly Increasing Input Information Density for Vision Transformers on Small Datasets
To boost the performance of vision Transformers on small datasets, this paper proposes to explicitly increase the input information density in the frequency domain.
Miti-DETR: Object Detection based on Transformers with Mitigatory Self-Attention Convergence
Object Detection with Transformers (DETR) and related works reach or even surpass the highly-optimized Faster-RCNN baseline with self-attention network architectures.
SAdam: A Variant of Adam for Strongly Convex Functions
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.
Boosting Occluded Image Classification via Subspace Decomposition Based Estimation of Deep Features
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.
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.
A Discriminative Channel Diversification Network for Image Classification
Channel attention mechanisms in convolutional neural networks have been proven to be effective in various computer vision tasks.
Learning Depth from Single Images with Deep Neural Network Embedding Focal Length
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.
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.
Vision-based Real-Time Aerial Object Localization and Tracking for UAV Sensing System
The paper focuses on the problem of vision-based obstacle detection and tracking for unmanned aerial vehicle navigation.
Robust Structure from Motion in the Presence of Outliers and Missing Data
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
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.
Tracking Completion
A fundamental component of modern trackers is an online learned tracking model, which is typically modeled either globally or locally.
Natural Scene Recognition Based on Superpixels and Deep Boltzmann Machines
However, the DBM is limited in scene recognition due to the fact that natural scene images are usually very large.
A Novel Feature Extraction Method for Scene Recognition Based on Centered Convolutional Restricted Boltzmann Machines
In this paper, a novel feature extraction method, named Centered Convolutional Restricted Boltzmann Machines (CCRBM), is proposed for scene recognition.
An Efficient Approach for Polyps Detection in Endoscopic Videos Based on Faster R-CNN
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.
MDCN: Multi-Scale, Deep Inception Convolutional Neural Networks for Efficient Object Detection
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.
Adversarially Approximated Autoencoder for Image Generation and Manipulation
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.
Adaptivity and Optimality: A Universal Algorithm for Online Convex Optimization
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.
Toward Learning a Unified Many-to-Many Mapping for Diverse Image Translation
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.
Multi-Objective Generalized Linear Bandits
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.
Dual Adaptivity: A Universal Algorithm for Minimizing the Adaptive Regret of Convex Functions
Along this line of research, this paper presents the first universal algorithm for minimizing the adaptive regret of convex functions.
Bandit Convex Optimization in Non-stationary Environments
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.
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).
Direct Visual-Inertial Odometry with Semi-Dense Mapping
The first one, based on Direct Sparse Odometry (DSO), is to estimate the depths of candidate points for mapping and dense visual tracking.
Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization
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.
Stacked Wasserstein Autoencoder
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.
Adaptively Denoising Proposal Collection forWeakly Supervised Object Localization
In this paper, we address the problem of weakly supervisedobject localization (WSL), which trains a detection network on the datasetwith only image-level annotations.
Object Detection with Convolutional Neural Networks
In this chapter, we present a brief overview of the recent development in object detection using convolutional neural networks (CNN).
MDFN: Multi-Scale Deep Feature Learning Network for Object Detection
Compared with features produced in earlier layers, the deep features are better at expressing semantic and contextual information.
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.
Plug-and-Play Rescaling Based Crowd Counting in Static Images
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.
ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images
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.
Nearly Optimal Regret for Stochastic Linear Bandits with Heavy-Tailed Payoffs
In this paper, we study the problem of stochastic linear bandits with finite action sets.
Location-Aware Box Reasoning for Anchor-Based Single-Shot Object Detection
In this paper, we aim at single-shot object detectors and propose a location-aware anchor-based reasoning (LAAR) for the bounding boxes.
A Comparative Study on Polyp Classification using Convolutional Neural Networks
In this work, we compare the performance of the state-of-the-art general object classification models for polyp classification.
Classification of Noncoding RNA Elements Using Deep Convolutional Neural Networks
The paper proposes to employ deep convolutional neural networks (CNNs) to classify noncoding RNA (ncRNA) sequences.
Multi-Resolution Fusion and Multi-scale Input Priors Based Crowd Counting
The state-of-the-art patch rescaling module (PRM) based approaches prove to be very effective in improving the crowd counting performance.
Why Layer-Wise Learning is Hard to Scale-up and a Possible Solution via Accelerated Downsampling
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.
Stereo Frustums: A Siamese Pipeline for 3D Object Detection
The paper proposes a light-weighted stereo frustums matching module for 3D objection detection.
Deep Feature Augmentation for Occluded Image Classification
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).
Six-channel Image Representation for Cross-domain Object Detection
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.
SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images
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 #81 on
Semantic Segmentation
on NYU Depth v2
Classification of Long Noncoding RNA Elements Using Deep Convolutional Neural Networks and Siamese Networks
To this end, this paper first proposes anefficient approach to convert the RNA sequences into imagescharacterizing their base-pairing probability.
Online Convex Optimization with Continuous Switching Constraint
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.
Projection-free Distributed Online Learning with Sublinear Communication Complexity
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.
Colonoscopy Polyp Detection and Classification: Dataset Creation and Comparative Evaluations
This work can serve as a baseline for future research in polyp detection and classification.
Parallel Scale-wise Attention Network for Effective Scene Text Recognition
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.
A Simple yet Universal Strategy for Online Convex Optimization
In this paper, we propose a simple strategy for universal online convex optimization, which avoids these limitations.
A Fine-Grained Visual Attention Approach for Fingerspelling Recognition in the Wild
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.
Momentum Accelerates the Convergence of Stochastic AUPRC Maximization
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.
A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translation
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
Towards More Effective PRM-based Crowd Counting via A Multi-resolution Fusion and Attention Network
The paper focuses on improving the recent plug-and-play patch rescaling module (PRM) based approaches for crowd counting.
An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training
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.
Semantic Clustering based Deduction Learning for Image Recognition and Classification
The paper proposes a semantic clustering based deduction learning by mimicking the learning and thinking process of human brains.
In Defense of Subspace Tracker: Orthogonal Embedding for Visual Tracking
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.
Adaptive Oracle-Efficient Online Learning
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.
On Accelerated Perceptrons and Beyond
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 $\gamma > 0$.
Minimizing Dynamic Regret on Geodesic Metric Spaces
In this paper, we consider the sequential decision problem where the goal is to minimize the general dynamic regret on a complete Riemannian manifold.
Gender, Smoking History and Age Prediction from Laryngeal Images
In this study, we made the first endeavor to employ deep learning models to predict patient demographic information to improve detector model performance.
Faster Margin Maximization Rates for Generic and Adversarially Robust Optimization Methods
To address this limitation, we present a series of state-of-the-art implicit bias rates for mirror descent and steepest descent algorithms.
On Riemannian Projection-free Online Learning
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.
Edge-aware Multi-task Network for Integrating Quantification Segmentation and Uncertainty Prediction of Liver Tumor on Multi-modality Non-contrast MRI
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.
A New Dataset and Comparative Study for Aphid Cluster Detection
Aphids are one of the main threats to crops, rural families, and global food security.
On the Real-Time Semantic Segmentation of Aphid Clusters in the Wild
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.
Aphid Cluster Recognition and Detection in the Wild Using Deep Learning Models
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.
Extragradient Type Methods for Riemannian Variational Inequality Problems
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).
Disentangled Representation Learning for Controllable Person Image Generation
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.
Predicting Mitral Valve mTEER Surgery Outcomes Using Machine Learning and Deep Learning Techniques
Mitral Transcatheter Edge-to-Edge Repair (mTEER) is a medical procedure utilized for the treatment of mitral valve disorders.
Kitchen Food Waste Image Segmentation and Classification for Compost Nutrients Estimation
The escalating global concern over extensive food wastage necessitates innovative solutions to foster a net-zero lifestyle and reduce emissions.
Assessing Patient Eligibility for Inspire Therapy through Machine Learning and Deep Learning Models
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.
SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modules
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.
Multi-Layer Dense Attention Decoder for Polyp Segmentation
Detecting and segmenting polyps is crucial for expediting the diagnosis of colon cancer.
The intelligent prediction and assessment of financial information risk in the cloud computing model
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.
