Search Results for author: Yurong Chen

Found 30 papers, 13 papers with code

Dynamic Normalization and Relay for Video Action Recognition

no code implementations NeurIPS 2021 Dongqi Cai, Anbang Yao, Yurong Chen

In this paper, we present Dynamic Normalization and Relay (DNR), an improved normalization design, to augment the spatial-temporal representation learning of any deep action recognition model, adapting to small batch size training settings.

Action Recognition Representation Learning

P-WAE: Generalized Patch-Wasserstein Autoencoder for Anomaly Screening

1 code implementation9 Aug 2021 Yurong Chen

Anomaly detection plays a pivotal role in numerous real-world scenarios, such as industrial automation and manufacturing intelligence.

Anomaly Detection Variational Inference

Towards to Robust and Generalized Medical Image Segmentation Framework

1 code implementation9 Aug 2021 Yurong Chen

However, this paradigm is restricted in real-world clinical applications due to poor robustness and generalization.

Image Reconstruction Medical Image Segmentation +2

CASNet: Common Attribute Support Network for image instance and panoptic segmentation

no code implementations17 Jul 2020 Xiaolong Liu, Yuqing Hou, Anbang Yao, Yurong Chen, Keqiang Li

Given the insight that pixels belonging to one instance have one or more common attributes of current instance, we bring up an one-stage instance segmentation network named Common Attribute Support Network (CASNet), which realizes instance segmentation by predicting and clustering common attributes.

Instance Segmentation Object Detection +1

On Connections between Regularizations for Improving DNN Robustness

no code implementations4 Jul 2020 Yiwen Guo, Long Chen, Yurong Chen, Chang-Shui Zhang

This paper analyzes regularization terms proposed recently for improving the adversarial robustness of deep neural networks (DNNs), from a theoretical point of view.

Adversarial Robustness Image Classification

Adversarial Attack on Hierarchical Graph Pooling Neural Networks

no code implementations23 May 2020 Haoteng Tang, Guixiang Ma, Yurong Chen, Lei Guo, Wei Wang, Bo Zeng, Liang Zhan

However, most of the existing work in this area focus on the GNNs for node-level tasks, while little work has been done to study the robustness of the GNNs for the graph classification task.

Adversarial Attack Classification +4

Learning Two-View Correspondences and Geometry Using Order-Aware Network

1 code implementation ICCV 2019 Jiahui Zhang, Dawei Sun, Zixin Luo, Anbang Yao, Lei Zhou, Tianwei Shen, Yurong Chen, Long Quan, Hongen Liao

First, to capture the local context of sparse correspondences, the network clusters unordered input correspondences by learning a soft assignment matrix.

Efficient Semantic Scene Completion Network with Spatial Group Convolution

1 code implementation ECCV 2018 Jiahui Zhang, Hao Zhao, Anbang Yao, Yurong Chen, Li Zhang, Hongen Liao

We introduce Spatial Group Convolution (SGC) for accelerating the computation of 3D dense prediction tasks.

A Closed-form Solution to Universal Style Transfer

2 code implementations ICCV 2019 Ming Lu, Hao Zhao, Anbang Yao, Yurong Chen, Feng Xu, Li Zhang

Although plenty of methods have been proposed, a theoretical analysis of feature transform is still missing.

Style Transfer

Sparse DNNs with Improved Adversarial Robustness

no code implementations NeurIPS 2018 Yiwen Guo, Chao Zhang, Chang-Shui Zhang, Yurong Chen

Deep neural networks (DNNs) are computationally/memory-intensive and vulnerable to adversarial attacks, making them prohibitive in some real-world applications.

Adversarial Robustness General Classification

SnapQuant: A Probabilistic and Nested Parameterization for Binary Networks

no code implementations27 Sep 2018 Kuan Wang, Hao Zhao, Anbang Yao, Aojun Zhou, Dawei Sun, Yurong Chen

During the training phase, we generate binary weights on-the-fly since what we actually maintain is the policy network, and all the binary weights are used in a burn-after-reading style.

Object Detection from Scratch with Deep Supervision

1 code implementation25 Sep 2018 Zhiqiang Shen, Zhuang Liu, Jianguo Li, Yu-Gang Jiang, Yurong Chen, xiangyang xue

Thus, a better solution to handle these critical problems is to train object detectors from scratch, which motivates our proposed method.

Fine-tuning General Classification +1

Network Decoupling: From Regular to Depthwise Separable Convolutions

1 code implementation16 Aug 2018 Jianbo Guo, Yuxi Li, Weiyao Lin, Yurong Chen, Jianguo Li

Depthwise separable convolution has shown great efficiency in network design, but requires time-consuming training procedure with full training-set available.

Object Detection

Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks

no code implementations CVPR 2018 Aojun Zhou, Anbang Yao, Kuan Wang, Yurong Chen

Through explicitly regularizing the loss perturbation and the weight approximation error in an incremental way, we show that such a new optimization method is theoretically reasonable and practically effective.

Quantization

DSOD: Learning Deeply Supervised Object Detectors from Scratch

4 code implementations ICCV 2017 Zhiqiang Shen, Zhuang Liu, Jianguo Li, Yu-Gang Jiang, Yurong Chen, xiangyang xue

State-of-the-art object objectors rely heavily on the off-the-shelf networks pre-trained on large-scale classification datasets like ImageNet, which incurs learning bias due to the difference on both the loss functions and the category distributions between classification and detection tasks.

Fine-tuning General Classification +1

Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization

1 code implementation3 Aug 2017 Yinpeng Dong, Renkun Ni, Jianguo Li, Yurong Chen, Jun Zhu, Hang Su

This procedure can greatly compensate the quantization error and thus yield better accuracy for low-bit DNNs.

Quantization

Network Sketching: Exploiting Binary Structure in Deep CNNs

no code implementations CVPR 2017 Yiwen Guo, Anbang Yao, Hao Zhao, Yurong Chen

Convolutional neural networks (CNNs) with deep architectures have substantially advanced the state-of-the-art in computer vision tasks.

Weakly Supervised Dense Video Captioning

no code implementations CVPR 2017 Zhiqiang Shen, Jianguo Li, Zhou Su, Minjun Li, Yurong Chen, Yu-Gang Jiang, xiangyang xue

This paper focuses on a novel and challenging vision task, dense video captioning, which aims to automatically describe a video clip with multiple informative and diverse caption sentences.

Dense Video Captioning Language Modelling +1

Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights

3 code implementations10 Feb 2017 Aojun Zhou, Anbang Yao, Yiwen Guo, Lin Xu, Yurong Chen

The weights in the other group are responsible to compensate for the accuracy loss from the quantization, thus they are the ones to be re-trained.

Quantization

Dynamic Network Surgery for Efficient DNNs

4 code implementations NeurIPS 2016 Yiwen Guo, Anbang Yao, Yurong Chen

In this paper, we propose a novel network compression method called dynamic network surgery, which can remarkably reduce the network complexity by making on-the-fly connection pruning.

HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection

no code implementations CVPR 2016 Tao Kong, Anbang Yao, Yurong Chen, Fuchun Sun

Almost all of the current top-performing object detection networks employ region proposals to guide the search for object instances.

Object Detection Region Proposal

Deep Attributes from Context-Aware Regional Neural Codes

no code implementations8 Sep 2015 Jianwei Luo, Jianguo Li, Jun Wang, Zhiguo Jiang, Yurong Chen

Results show that deep attribute approaches achieve state-of-the-art results, and outperforms existing peer methods with a significant margin, even though some benchmarks have little overlap of concepts with the pre-trained CNN models.

General Classification Image Classification

Large-scale Supervised Hierarchical Feature Learning for Face Recognition

no code implementations6 Jul 2014 Jianguo Li, Yurong Chen

Second, the face image is further represented by patches of picked channels, and we search from the over-complete patch pool to activate only those most discriminant patches.

Face Recognition

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