388 citations · 803 across the 14 of their papers we have counts for
14 papers
Tuning Pre-trained Model via Moment Probing
Mingze Gao, Qilong Wang, Zhenyi Lin +3
Recently, efficient fine-tuning of large-scale pre-trained models has attracted increasing research interests, where linear probing (LP) as a fundamental module is involved in expl…
Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification
Jiangtao Xie, Fei Long, Jiaming Lv +2
Few-shot classification is a challenging problem as only very few training examples are given for each new task. One of the effective research lines to address this challenge focus…
What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective
Qilong Wang, Li Zhang, Banggu Wu +4
Recent works have demonstrated that global covariance pooling (GCP) has the ability to improve performance of deep convolutional neural networks (CNNs) on visual classification tas…
Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network
Longyin Wen, Dawei Du, Pengfei Zhu +4
This paper proposes a space-time multi-scale attention network (STANet) to solve density map estimation, localization and tracking in dense crowds of video clips captured by drones…
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
Qilong Wang, Banggu Wu, Pengfei Zhu +3
Recently, channel attention mechanism has demonstrated to offer great potential in improving the performance of deep convolutional neural networks (CNNs). However, most existing me…
Neural Blind Deconvolution Using Deep Priors
Dongwei Ren, Kai Zhang, Qilong Wang +2
Blind deconvolution is a classical yet challenging low-level vision problem with many real-world applications. Traditional maximum a posterior (MAP) based methods rely heavily on f…
Data Augmentation for Object Detection via Progressive and Selective Instance-Switching
Hao Wang, Qilong Wang, Fan Yang +2
Collection of massive well-annotated samples is effective in improving object detection performance but is extremely laborious and costly. Instead of data collection and annotation…
Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization
Qilong Wang, Jiangtao Xie, Wangmeng Zuo +2
Compared with global average pooling in existing deep convolutional neural networks (CNNs), global covariance pooling can capture richer statistics of deep features, having potenti…
Global Second-order Pooling Convolutional Networks
Zilin Gao, Jiangtao Xie, Qilong Wang +1
Deep Convolutional Networks (ConvNets) are fundamental to, besides large-scale visual recognition, a lot of vision tasks. As the primary goal of the ConvNets is to characterize com…
Multi-scale Location-aware Kernel Representation for Object Detection
Hao Wang, Qilong Wang, Mingqi Gao +2
Although Faster R-CNN and its variants have shown promising performance in object detection, they only exploit simple first-order representation of object proposals for final class…
Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization
Peihua Li, Jiangtao Xie, Qilong Wang +1
Global covariance pooling in convolutional neural networks has achieved impressive improvement over the classical first-order pooling. Recent works have shown matrix square root no…
Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation
Hongliang Yan, Yukang Ding, Peihua Li +3
In domain adaptation, maximum mean discrepancy (MMD) has been widely adopted as a discrepancy metric between the distributions of source and target domains. However, existing MMD-b…
Is Second-order Information Helpful for Large-scale Visual Recognition?
Peihua Li, Jiangtao Xie, Qilong Wang +1
By stacking layers of convolution and nonlinearity, convolutional networks (ConvNets) effectively learn from low-level to high-level features and discriminative representations. Si…
Towards Effective Codebookless Model for Image Classification
Qilong Wang, Peihua Li, Lei Zhang +1
The bag-of-features (BoF) model for image classification has been thoroughly studied over the last decade. Different from the widely used BoF methods which modeled images with a pr…