Search Results for author: Yanan sun

Found 42 papers, 14 papers with code

CN: Channel Normalization For Point Cloud Recognition

no code implementations ECCV 2020 Zetong Yang, Yanan sun, Shu Liu, Xiaojuan Qi, Jiaya Jia

In 3D recognition, to fuse multi-scale structure information, existing methods apply hierarchical frameworks stacked by multiple fusion layers for integrating current relative locations with structure information from the previous level.

Efficient Evaluation Methods for Neural Architecture Search: A Survey

no code implementations14 Jan 2023 Xiangning Xie, Xiaotian Song, Zeqiong Lv, Gary G. Yen, Weiping Ding, Yanan sun

In surveying each category, we further discuss the design principles and analyze the strength and weaknesses to clarify the landscape of existing EEMs, thus making easily understanding the research trends of EEMs.

Neural Architecture Search

Differentiable Search of Accurate and Robust Architectures

no code implementations28 Dec 2022 Yuwei Ou, Xiangning Xie, Shangce Gao, Yanan sun, Kay Chen Tan, Jiancheng Lv

Deep neural networks (DNNs) are found to be vulnerable to adversarial attacks, and various methods have been proposed for the defense.

DAS: Neural Architecture Search via Distinguishing Activation Score

no code implementations23 Dec 2022 Yuqiao Liu, Haipeng Li, Yanan sun, Shuaicheng Liu

NAS without training (WOT) score is such a metric, which estimates the final trained accuracy of the architecture through the ability to distinguish different inputs in the activation layer.

Neural Architecture Search

H-VFI: Hierarchical Frame Interpolation for Videos with Large Motions

no code implementations21 Nov 2022 Changlin Li, Guangyang Wu, Yanan sun, Xin Tao, Chi-Keung Tang, Yu-Wing Tai

The learnt deformable kernel is then utilized in convolving the input frames for predicting the interpolated frame.

Video Frame Interpolation

Bridge the Gap Between Architecture Spaces via A Cross-Domain Predictor

1 code implementation NeurIPS 2022 Yuqiao Liu, Yehui Tang ~Yehui_Tang1, Zeqiong Lv, Yunhe Wang, Yanan sun

To solve this issue, we propose a Cross-Domain Predictor (CDP), which is trained based on the existing NAS benchmark datasets (e. g., NAS-Bench-101), but can be used to find high-performance architectures in large-scale search spaces.

Neural Architecture Search

Analysis of Expected Hitting Time for Designing Evolutionary Neural Architecture Search Algorithms

no code implementations11 Oct 2022 Zeqiong Lv, Chao Qian, Gary G. Yen, Yanan sun

Evolutionary computation-based neural architecture search (ENAS) is a popular technique for automating architecture design of deep neural networks.

Neural Architecture Search

Continuously Controllable Facial Expression Editing in Talking Face Videos

no code implementations17 Sep 2022 Zhiyao Sun, Yu-Hui Wen, Tian Lv, Yanan sun, Ziyang Zhang, Yaoyuan Wang, Yong-Jin Liu

In this paper, we propose a high-quality facial expression editing method for talking face videos, allowing the user to control the target emotion in the edited video continuously.

Image-to-Image Translation Video Generation

Architecture Augmentation for Performance Predictor Based on Graph Isomorphism

no code implementations3 Jul 2022 Xiangning Xie, Yuqiao Liu, Yanan sun, Mengjie Zhang, Kay Chen Tan

Performance predictors can greatly alleviate the prohibitive cost of NAS by directly predicting the performance of DNNs.

Neural Architecture Search

Human Instance Matting via Mutual Guidance and Multi-Instance Refinement

1 code implementation CVPR 2022 Yanan sun, Chi-Keung Tang, Yu-Wing Tai

A new instance matting metric called instance matting quality (IMQ) is proposed, which addresses the absence of a unified and fair means of evaluation emphasizing both instance recognition and matting quality.

Image Matting Instance Segmentation +1

Automating Neural Architecture Design without Search

no code implementations21 Apr 2022 Zixuan Liang, Yanan sun

Specifically, the proposed approach is built by learning the knowledge of high-level experts in designing state-of-the-art architectures, and then the new architecture is directly generated upon the knowledge learned.

Link Prediction

Dynamic Neural Textures: Generating Talking-Face Videos with Continuously Controllable Expressions

no code implementations13 Apr 2022 Zipeng Ye, Zhiyao Sun, Yu-Hui Wen, Yanan sun, Tian Lv, Ran Yi, Yong-Jin Liu

In this paper, we propose a method to generate talking-face videos with continuously controllable expressions in real-time.

Video Generation

A Unified Query-based Paradigm for Point Cloud Understanding

1 code implementation CVPR 2022 Zetong Yang, Li Jiang, Yanan sun, Bernt Schiele, Jiaya Jia

This is achieved by introducing an intermediate representation, i. e., Q-representation, in the querying stage to serve as a bridge between the embedding stage and task heads.

Autonomous Driving object-detection +2

Evolving Deep Neural Networks for Collaborative Filtering

no code implementations15 Nov 2021 Yuhan Fang, Yuqiao Liu, Yanan sun

As a consequence, it requires the designers to develop expertise in both CF and DNNs, which limits the application of deep learning methods in CF and the accuracy of recommended results.

Collaborative Filtering Recommendation Systems

BenchENAS: A Benchmarking Platform for Evolutionary Neural Architecture Search

no code implementations9 Aug 2021 Xiangning Xie, Yuqiao Liu, Yanan sun, Gary G. Yen, Bing Xue, Mengjie Zhang

The paper conducts efficient comparison experiments on eight ENAS algorithms with high GPU utilization on this platform.

Neural Architecture Search

Homogeneous Architecture Augmentation for Neural Predictor

1 code implementation ICCV 2021 Yuqiao Liu, Yehui Tang, Yanan sun

Specifically, a homogeneous architecture augmentation algorithm is proposed in HAAP to generate sufficient training data taking the use of homogeneous representation.

Neural Architecture Search

Autoregressive Stylized Motion Synthesis With Generative Flow

no code implementations CVPR 2021 Yu-Hui Wen, Zhipeng Yang, Hongbo Fu, Lin Gao, Yanan sun, Yong-Jin Liu

Motion style transfer is an important problem in many computer graphics and computer vision applications, including human animation, games, and robotics.

Motion Style Transfer Style Transfer

Heart-Darts: Classification of Heartbeats Using Differentiable Architecture Search

no code implementations3 May 2021 Jindi Lv, Qing Ye, Yanan sun, Juan Zhao, Jiancheng Lv

In this paper, we propose a novel approach, Heart-Darts, to efficiently classify the ECG signals by automatically designing the CNN model with the differentiable architecture search (i. e., Darts, a cell-based neural architecture search method).

Arrhythmia Detection Classification +3

Deep Video Matting via Spatio-Temporal Alignment and Aggregation

1 code implementation CVPR 2021 Yanan sun, Guanzhi Wang, Qiao Gu, Chi-Keung Tang, Yu-Wing Tai

Despite the significant progress made by deep learning in natural image matting, there has been so far no representative work on deep learning for video matting due to the inherent technical challenges in reasoning temporal domain and lack of large-scale video matting datasets.

Image Matting Optical Flow Estimation +1

Semantic Image Matting

1 code implementation CVPR 2021 Yanan sun, Chi-Keung Tang, Yu-Wing Tai

Specifically, we consider and learn 20 classes of matting patterns, and propose to extend the conventional trimap to semantic trimap.

Semantic Image Matting Transparent objects

A Novel Training Protocol for Performance Predictors of Evolutionary Neural Architecture Search Algorithms

no code implementations30 Aug 2020 Yanan Sun, Xian Sun, Yuhan Fang, Gary Yen

Performance predictors are a type of regression models which can assist to accomplish the search, while without exerting much computational resource.

Neural Architecture Search regression

Evolving Deep Convolutional Neural Networks for Hyperspectral Image Denoising

no code implementations15 Aug 2020 Yuqiao Liu, Yanan sun, Bing Xue, Mengjie Zhang

Hyperspectral images (HSIs) are susceptible to various noise factors leading to the loss of information, and the noise restricts the subsequent HSIs object detection and classification tasks.

Hyperspectral Image Denoising Image Denoising +2

DBS: Dynamic Batch Size For Distributed Deep Neural Network Training

1 code implementation23 Jul 2020 Qing Ye, Yuhao Zhou, Mingjia Shi, Yanan sun, Jiancheng Lv

Specifically, the performance of each worker is evaluatedfirst based on the fact in the previous epoch, and then the batch size and datasetpartition are dynamically adjusted in consideration of the current performanceof the worker, thereby improving the utilization of the cluster.

3D-CariGAN: An End-to-End Solution to 3D Caricature Generation from Face Photos

1 code implementation15 Mar 2020 Zipeng Ye, Mengfei Xia, Yanan sun, Ran Yi, MinJing Yu, Juyong Zhang, Yu-Kun Lai, Yong-Jin Liu

The most challenging issue for our system is that the source domain of face photos (characterized by normal 2D faces) is significantly different from the target domain of 3D caricatures (characterized by 3D exaggerated face shapes and textures).

Caricature

3DSSD: Point-based 3D Single Stage Object Detector

2 code implementations CVPR 2020 Zetong Yang, Yanan sun, Shu Liu, Jiaya Jia

Our method outperforms all state-of-the-art voxel-based single stage methods by a large margin, and has comparable performance to two stage point-based methods as well, with inference speed more than 25 FPS, 2x faster than former state-of-the-art point-based methods.

ArcText: A Unified Text Approach to Describing Convolutional Neural Network Architectures

no code implementations16 Feb 2020 Yanan Sun, Ziyao Ren, Gary G. Yen, Bing Xue, Mengjie Zhang, Jiancheng Lv

Data mining on existing CNN can discover useful patterns and fundamental sub-comments from their architectures, providing researchers with strong prior knowledge to design proper CNN architectures when they have no expertise in CNNs.

Evolving Deep Neural Networks by Multi-objective Particle Swarm Optimization for Image Classification

1 code implementation21 Mar 2019 Bin Wang, Yanan sun, Bing Xue, Mengjie Zhang

In recent years, convolutional neural networks (CNNs) have become deeper in order to achieve better classification accuracy in image classification.

Classification General Classification +1

A Hybrid GA-PSO Method for Evolving Architecture and Short Connections of Deep Convolutional Neural Networks

no code implementations10 Mar 2019 Bin Wang, Yanan sun, Bing Xue, Mengjie Zhang

Three major contributions of this work are: Firstly, a new encoding strategy is proposed to encode a CNN, where the architecture and the shortcut connections are encoded separately; Secondly, a hybrid two-level EC method, which combines particle swarm optimisation and genetic algorithms, is developed to search for the optimal CNNs; Lastly, an adjustable learning rate is introduced for the fitness evaluations, which provides a better learning rate for the training process given a fixed number of epochs.

General Classification Image Classification

Automatically Evolving CNN Architectures Based on Blocks

no code implementations28 Oct 2018 Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen

The proposed algorithm is evaluated on CIFAR10 and CIFAR100 against 18 state-of-the-art peer competitors.

General Classification

A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification

no code implementations20 Aug 2018 Bin Wang, Yanan sun, Bing Xue, Mengjie Zhang

In this paper, a new hybrid differential evolution (DE) algorithm with a newly added crossover operator is proposed to evolve the architectures of CNNs of any lengths, which is named DECNN.

General Classification Image Classification

Automatically designing CNN architectures using genetic algorithm for image classification

4 code implementations11 Aug 2018 Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen

Convolutional Neural Networks (CNNs) have gained a remarkable success on many image classification tasks in recent years.

Classification General Classification +1

Evolving Deep Convolutional Neural Networks by Variable-length Particle Swarm Optimization for Image Classification

no code implementations17 Mar 2018 Bin Wang, Yanan sun, Bing Xue, Mengjie Zhang

Convolutional neural networks (CNNs) are one of the most effective deep learning methods to solve image classification problems, but the best architecture of a CNN to solve a specific problem can be extremely complicated and hard to design.

General Classification Image Classification

IGD Indicator-based Evolutionary Algorithm for Many-objective Optimization Problems

no code implementations24 Feb 2018 Yanan Sun, Gary G. Yen, Zhang Yi

Inverted Generational Distance (IGD) has been widely considered as a reliable performance indicator to concurrently quantify the convergence and diversity of multi- and many-objective evolutionary algorithms.

Improved Regularity Model-based EDA for Many-objective Optimization

no code implementations24 Feb 2018 Yanan Sun, Gary G. Yen, Zhang Yi

Finally, by assigning the Pareto-optimal solutions to the uniformly distributed reference vectors, a set of solutions with excellent diversity and convergence is obtained.

Dimensionality Reduction

Evolving Unsupervised Deep Neural Networks for Learning Meaningful Representations

no code implementations13 Dec 2017 Yanan Sun, Gary G. Yen, Zhang Yi

Specifically, error classification rate on MNIST with $1. 15\%$ is reached by the proposed algorithm consistently, which is a very promising result against state-of-the-art unsupervised DL algorithms.

General Classification

A Particle Swarm Optimization-based Flexible Convolutional Auto-Encoder for Image Classification

1 code implementation13 Dec 2017 Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen

Convolutional auto-encoders have shown their remarkable performance in stacking to deep convolutional neural networks for classifying image data during past several years.

General Classification Image Classification

Evolving Deep Convolutional Neural Networks for Image Classification

1 code implementation30 Oct 2017 Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen

Evolutionary computation methods have been successfully applied to neural networks since two decades ago, while those methods cannot scale well to the modern deep neural networks due to the complicated architectures and large quantities of connection weights.

Classification General Classification +1

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