Search Results for author: Peihua Li

Found 19 papers, 14 papers with code

DropCov: A Simple yet Effective Method for Improving Deep Architectures

1 code implementation NeurIPS 2022 Conference 2023 Qilong Wang, Mingze Gao, Zhaolin Zhang, Jiangtao Xie, Peihua Li, QinGhua Hu

Particularly, we for the first time show that \textit{effective post-normalization can make a good trade-off between representation decorrelation and information preservation for GCP, which are crucial to alleviate over-fitting and increase representation ability of deep GCP networks, respectively}.

Temporal-attentive Covariance Pooling Networks for Video Recognition

1 code implementation NeurIPS 2021 Zilin Gao, Qilong Wang, Bingbing Zhang, QinGhua Hu, Peihua Li

Then, a temporal covariance pooling performs temporal pooling of the attentive covariance representations to characterize both intra-frame correlations and inter-frame cross-correlations of the calibrated features.

Video Recognition

So-ViT: Mind Visual Tokens for Vision Transformer

1 code implementation22 Apr 2021 Jiangtao Xie, Ruiren Zeng, Qilong Wang, Ziqi Zhou, Peihua Li

Therefore, we propose a new classification paradigm, where the second-order, cross-covariance pooling of visual tokens is combined with class token for final classification.

Classification General Classification

What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective

1 code implementation CVPR 2020 Qilong Wang, Li Zhang, Banggu Wu, Dongwei Ren, Peihua Li, WangMeng Zuo, QinGhua Hu

Recent works have demonstrated that global covariance pooling (GCP) has the ability to improve performance of deep convolutional neural networks (CNNs) on visual classification task.

Instance Segmentation object-detection +2

ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

12 code implementations CVPR 2020 Qilong Wang, Banggu Wu, Pengfei Zhu, Peihua Li, WangMeng Zuo, QinGhua Hu

By dissecting the channel attention module in SENet, we empirically show avoiding dimensionality reduction is important for learning channel attention, and appropriate cross-channel interaction can preserve performance while significantly decreasing model complexity.

Dimensionality Reduction Image Classification +4

Global Gated Mixture of Second-order Pooling for Improving Deep Convolutional Neural Networks

1 code implementation NeurIPS 2018 Qilong Wang, Zilin Gao, Jiangtao Xie, WangMeng Zuo, Peihua Li

However, both GAP and existing HOP methods assume unimodal distributions, which cannot fully capture statistics of convolutional activations, limiting representation ability of deep CNNs, especially for samples with complex contents.

Global Second-order Pooling Convolutional Networks

1 code implementation CVPR 2019 Zilin Gao, Jiangtao Xie, Qilong Wang, Peihua Li

Deep Convolutional Networks (ConvNets) are fundamental to, besides large-scale visual recognition, a lot of vision tasks.

Object Recognition

Multi-scale Location-aware Kernel Representation for Object Detection

2 code implementations CVPR 2018 Hao Wang, Qilong Wang, Mingqi Gao, Peihua Li, WangMeng Zuo

Our MLKP can be efficiently computed on a modified multi-scale feature map using a low-dimensional polynomial kernel approximation. Moreover, different from existing orderless global representations based on high-order statistics, our proposed MLKP is location retentive and sensitive so that it can be flexibly adopted to object detection.

General Classification Object +2

G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition

no code implementations CVPR 2017 Qilong Wang, Peihua Li, Lei Zhang

Recently, plugging trainable structural layers into deep convolutional neural networks (CNNs) as image representations has made promising progress.

Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation

3 code implementations CVPR 2017 Hongliang Yan, Yukang Ding, Peihua Li, Qilong Wang, Yong Xu, WangMeng Zuo

Specifically, we introduce class-specific auxiliary weights into the original MMD for exploiting the class prior probability on source and target domains, whose challenge lies in the fact that the class label in target domain is unavailable.

Unsupervised Domain Adaptation

Is Second-order Information Helpful for Large-scale Visual Recognition?

1 code implementation ICCV 2017 Peihua Li, Jiangtao Xie, Qilong Wang, WangMeng Zuo

The main challenges involved are robust covariance estimation given a small sample of large-dimensional features and usage of the manifold structure of covariance matrices.

Object Recognition

End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks

no code implementations26 Jul 2016 Yifan Wang, Lijun Wang, Hongyu Wang, Peihua Li

In this paper, we seek an alternative and propose a new image SR method, which jointly learns the feature extraction, upsampling and HR reconstruction modules, yielding a completely end-to-end trainable deep CNN.

Image Super-Resolution

RAID-G: Robust Estimation of Approximate Infinite Dimensional Gaussian With Application to Material Recognition

no code implementations CVPR 2016 Qilong Wang, Peihua Li, WangMeng Zuo, Lei Zhang

Infinite dimensional covariance descriptors can provide richer and more discriminative information than their low dimensional counterparts.

Material Recognition

Towards Effective Codebookless Model for Image Classification

no code implementations9 Jul 2015 Qilong Wang, Peihua Li, Lei Zhang, WangMeng Zuo

The bag-of-features (BoF) model for image classification has been thoroughly studied over the last decade.

Classification General Classification +2

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