Search Results for author: Pengfei Xu

Found 33 papers, 12 papers with code

S4OD: Semi-Supervised learning for Single-Stage Object Detection

no code implementations9 Apr 2022 Yueming Zhang, Xingxu Yao, Chao Liu, Feng Chen, Xiaolin Song, Tengfei Xing, Runbo Hu, Hua Chai, Pengfei Xu, Guoshan Zhang

In this paper, we design a dynamic self-adaptive threshold (DSAT) strategy in classification branch, which can automatically select pseudo labels to achieve an optimal trade-off between quality and quantity.

Object Detection Semi-Supervised Object Detection

A Critical Analysis of Image-based Camera Pose Estimation Techniques

no code implementations15 Jan 2022 Meng Xu, Youchen Wang, Bin Xu, Jun Zhang, Jian Ren, Stefan Poslad, Pengfei Xu

Camera, and associated with its objects within the field of view, localization could benefit many computer vision fields, such as autonomous driving, robot navigation, and augmented reality (AR).

Autonomous Driving Camera Localization +2

2nd Place Solution for VisDA 2021 Challenge -- Universally Domain Adaptive Image Recognition

no code implementations27 Oct 2021 Haojin Liao, Xiaolin Song, Sicheng Zhao, Shanghang Zhang, Xiangyu Yue, Xingxu Yao, Yueming Zhang, Tengfei Xing, Pengfei Xu, Qiang Wang

The Visual Domain Adaptation (VisDA) 2021 Challenge calls for unsupervised domain adaptation (UDA) methods that can deal with both input distribution shift and label set variance between the source and target domains.

Universal Domain Adaptation Unsupervised Domain Adaptation

Multi-Source Domain Adaptation for Object Detection

no code implementations ICCV 2021 Xingxu Yao, Sicheng Zhao, Pengfei Xu, Jufeng Yang

To reduce annotation labor associated with object detection, an increasing number of studies focus on transferring the learned knowledge from a labeled source domain to another unlabeled target domain.

Domain Adaptation Object Detection +1

A Comprehensive Survey of Scene Graphs: Generation and Application

no code implementations17 Mar 2021 Xiaojun Chang, Pengzhen Ren, Pengfei Xu, Zhihui Li, Xiaojiang Chen, Alex Hauptmann

For example, given an image, we want to not only detect and recognize objects in the image, but also know the relationship between objects (visual relationship detection), and generate a text description (image captioning) based on the image content.

Image Captioning Question Answering +4

Communication-efficient Byzantine-robust distributed learning with statistical guarantee

no code implementations28 Feb 2021 Xingcai Zhou, Le Chang, Pengfei Xu, Shaogao Lv

To address the two issues simultaneously, this paper develops two communication-efficient and robust distributed learning algorithms for convex problems.

SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training

1 code implementation4 Jan 2021 Xiaohan Chen, Yang Zhao, Yue Wang, Pengfei Xu, Haoran You, Chaojian Li, Yonggan Fu, Yingyan Lin, Zhangyang Wang

Results show that: 1) applied to inference, SD achieves up to 2. 44x energy efficiency as evaluated via real hardware implementations; 2) applied to training, SD leads to 10. 56x and 4. 48x reduction in the storage and training energy, with negligible accuracy loss compared to state-of-the-art training baselines.

Emotional Semantics-Preserved and Feature-Aligned CycleGAN for Visual Emotion Adaptation

no code implementations25 Nov 2020 Sicheng Zhao, Xuanbai Chen, Xiangyu Yue, Chuang Lin, Pengfei Xu, Ravi Krishna, Jufeng Yang, Guiguang Ding, Alberto L. Sangiovanni-Vincentelli, Kurt Keutzer

First, we generate an adapted domain to align the source and target domains on the pixel-level by improving CycleGAN with a multi-scale structured cycle-consistency loss.

Emotion Classification Emotion Recognition +1

Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources

1 code implementation17 Nov 2020 Sicheng Zhao, Yang Xiao, Jiang Guo, Xiangyu Yue, Jufeng Yang, Ravi Krishna, Pengfei Xu, Kurt Keutzer

C-CycleGAN transfers source samples at instance-level to an intermediate domain that is closer to the target domain with sentiment semantics preserved and without losing discriminative features.

Domain Adaptation Sentiment Analysis

ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation

no code implementations7 Sep 2020 Sicheng Zhao, Yezhen Wang, Bo Li, Bichen Wu, Yang Gao, Pengfei Xu, Trevor Darrell, Kurt Keutzer

They require prior knowledge of real-world statistics and ignore the pixel-level dropout noise gap and the spatial feature gap between different domains.

Autonomous Driving Domain Adaptation +2

Emotion-Based End-to-End Matching Between Image and Music in Valence-Arousal Space

1 code implementation22 Aug 2020 Sicheng Zhao, Yaxian Li, Xingxu Yao, Wei-Zhi Nie, Pengfei Xu, Jufeng Yang, Kurt Keutzer

In this paper, we study end-to-end matching between image and music based on emotions in the continuous valence-arousal (VA) space.

Metric Learning

Rethinking Distributional Matching Based Domain Adaptation

no code implementations23 Jun 2020 Bo Li, Yezhen Wang, Tong Che, Shanghang Zhang, Sicheng Zhao, Pengfei Xu, Wei Zhou, Yoshua Bengio, Kurt Keutzer

In this paper, in order to devise robust DA algorithms, we first systematically analyze the limitations of DM based methods, and then build new benchmarks with more realistic domain shifts to evaluate the well-accepted DM methods.

Domain Adaptation

TIMELY: Pushing Data Movements and Interfaces in PIM Accelerators Towards Local and in Time Domain

no code implementations3 May 2020 Weitao Li, Pengfei Xu, Yang Zhao, Haitong Li, Yuan Xie, Yingyan Lin

Resistive-random-access-memory (ReRAM) based processing-in-memory (R$^2$PIM) accelerators show promise in bridging the gap between Internet of Thing devices' constrained resources and Convolutional/Deep Neural Networks' (CNNs/DNNs') prohibitive energy cost.

Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks

1 code implementation ICLR 2020 Haoran You, Chaojian Li, Pengfei Xu, Yonggan Fu, Yue Wang, Xiaohan Chen, Richard G. Baraniuk, Zhangyang Wang, Yingyan Lin

Finally, we leverage the existence of EB tickets and the proposed mask distance to develop efficient training methods, which are achieved by first identifying EB tickets via low-cost schemes, and then continuing to train merely the EB tickets towards the target accuracy.

Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey

no code implementations26 Feb 2020 Sicheng Zhao, Bo Li, Colorado Reed, Pengfei Xu, Kurt Keutzer

Therefore, transferring the learned knowledge from a separate, labeled source domain to an unlabeled or sparsely labeled target domain becomes an appealing alternative.

Domain Adaptation

DNN-Chip Predictor: An Analytical Performance Predictor for DNN Accelerators with Various Dataflows and Hardware Architectures

no code implementations26 Feb 2020 Yang Zhao, Chaojian Li, Yue Wang, Pengfei Xu, Yongan Zhang, Yingyan Lin

The recent breakthroughs in deep neural networks (DNNs) have spurred a tremendously increased demand for DNN accelerators.

MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation

1 code implementation19 Feb 2020 Sicheng Zhao, Bo Li, Xiangyu Yue, Pengfei Xu, Kurt Keutzer

Finally, feature-level alignment is performed between the aggregated domain and the target domain while training the task network.

Domain Adaptation Semantic Segmentation

AutoDNNchip: An Automated DNN Chip Predictor and Builder for Both FPGAs and ASICs

1 code implementation6 Jan 2020 Pengfei Xu, Xiaofan Zhang, Cong Hao, Yang Zhao, Yongan Zhang, Yue Wang, Chaojian Li, Zetong Guan, Deming Chen, Yingyan Lin

Specifically, AutoDNNchip consists of two integrated enablers: (1) a Chip Predictor, built on top of a graph-based accelerator representation, which can accurately and efficiently predict a DNN accelerator's energy, throughput, and area based on the DNN model parameters, hardware configuration, technology-based IPs, and platform constraints; and (2) a Chip Builder, which can automatically explore the design space of DNN chips (including IP selection, block configuration, resource balancing, etc.

Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference

1 code implementation3 Jan 2020 Jianghao Shen, Yonggan Fu, Yue Wang, Pengfei Xu, Zhangyang Wang, Yingyan Lin

The core idea of DFS is to hypothesize layer-wise quantization (to different bitwidths) as intermediate "soft" choices to be made between fully utilizing and skipping a layer.

Quantization

Multi-source Distilling Domain Adaptation

1 code implementation22 Nov 2019 Sicheng Zhao, Guangzhi Wang, Shanghang Zhang, Yang Gu, Yaxian Li, Zhichao Song, Pengfei Xu, Runbo Hu, Hua Chai, Kurt Keutzer

Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA).

Domain Adaptation Multi-Source Unsupervised Domain Adaptation

E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings

no code implementations NeurIPS 2019 Yue Wang, Ziyu Jiang, Xiaohan Chen, Pengfei Xu, Yang Zhao, Yingyan Lin, Zhangyang Wang

Extensive simulations and ablation studies, with real energy measurements from an FPGA board, confirm the superiority of our proposed strategies and demonstrate remarkable energy savings for training.

Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks

1 code implementation26 Sep 2019 Haoran You, Chaojian Li, Pengfei Xu, Yonggan Fu, Yue Wang, Xiaohan Chen, Richard G. Baraniuk, Zhangyang Wang, Yingyan Lin

In this paper, we discover for the first time that the winning tickets can be identified at the very early training stage, which we term as early-bird (EB) tickets, via low-cost training schemes (e. g., early stopping and low-precision training) at large learning rates.

ROAM: Recurrently Optimizing Tracking Model

no code implementations CVPR 2020 Tianyu Yang, Pengfei Xu, Runbo Hu, Hua Chai, Antoni B. Chan

In this paper, we design a tracking model consisting of response generation and bounding box regression, where the first component produces a heat map to indicate the presence of the object at different positions and the second part regresses the relative bounding box shifts to anchors mounted on sliding-window locations.

Meta-Learning Response Generation

Dual Dynamic Inference: Enabling More Efficient, Adaptive and Controllable Deep Inference

no code implementations10 Jul 2019 Yue Wang, Jianghao Shen, Ting-Kuei Hu, Pengfei Xu, Tan Nguyen, Richard Baraniuk, Zhangyang Wang, Yingyan Lin

State-of-the-art convolutional neural networks (CNNs) yield record-breaking predictive performance, yet at the cost of high-energy-consumption inference, that prohibits their widely deployments in resource-constrained Internet of Things (IoT) applications.

Performance Evaluation of Deep Learning Tools in Docker Containers

no code implementations9 Nov 2017 Pengfei Xu, Shaohuai Shi, Xiaowen Chu

We first benchmark the performance of system components (IO, CPU and GPU) in a docker container and the host system and compare the results to see if there's any difference.

Supervised Learning Based Algorithm Selection for Deep Neural Networks

no code implementations10 Feb 2017 Shaohuai Shi, Pengfei Xu, Xiaowen Chu

In this paper, we target at optimizing the operations of multiplying a matrix with the transpose of another matrix (referred to as NT operation hereafter), which contribute about half of the training time of fully connected deep neural networks.

Benchmarking State-of-the-Art Deep Learning Software Tools

no code implementations25 Aug 2016 Shaohuai Shi, Qiang Wang, Pengfei Xu, Xiaowen Chu

We first benchmark the running performance of these tools with three popular types of neural networks on two CPU platforms and three GPU platforms.

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