Search Results for author: Chen Feng

Found 63 papers, 32 papers with code

Self-Supervised Representation Learning with Cross-Context Learning between Global and Hypercolumn Features

no code implementations25 Aug 2023 Zheng Gao, Chen Feng, Ioannis Patras

Inspired by cross-modality learning, we extend this existing framework that only learns from global features by encouraging the global features and intermediate layer features to learn from each other.

Contrastive Learning Knowledge Distillation +1

Concavity-Induced Distance for Unoriented Point Cloud Decomposition

no code implementations19 Jun 2023 Ruoyu Wang, Yanfei Xue, Bharath Surianarayanan, Dong Tian, Chen Feng

We propose Concavity-induced Distance (CID) as a novel way to measure the dissimilarity between a pair of points in an unoriented point cloud.

Instance Segmentation Semantic Segmentation

Collaborative Multi-Object Tracking with Conformal Uncertainty Propagation

no code implementations25 Mar 2023 Sanbao Su, Songyang Han, Yiming Li, Zhili Zhang, Chen Feng, Caiwen Ding, Fei Miao

MOT-CUP demonstrates the importance of uncertainty quantification in both COD and MOT, and provides the first attempt to improve the accuracy and reduce the uncertainty in MOT based on COD through uncertainty propogation.

Autonomous Vehicles Conformal Prediction +5

MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset

1 code implementation CVPR 2023 Chen Feng, Ioannis Patras

More specifically, within the contrastive learning framework, for each sample our method generates soft-labels with the aid of coarse labels against other samples and another augmented view of the sample in question.

Contrastive Learning Learning with coarse labels

Among Us: Adversarially Robust Collaborative Perception by Consensus

1 code implementation16 Mar 2023 Yiming Li, Qi Fang, Jiamu Bai, Siheng Chen, Felix Juefei-Xu, Chen Feng

This leads to our hypothesize-and-verify framework: perception results with and without collaboration from a random subset of teammates are compared until reaching a consensus.

3D Object Detection Adversarial Defense +2

Committed Private Information Retrieval

1 code implementation3 Feb 2023 Quang Cao, Hong Yen Tran, Son Hoang Dau, Xun Yi, Emanuele Viterbo, Chen Feng, Yu-Chih Huang, Jingge Zhu, Stanislav Kruglik, Han Mao Kiah

A PIR scheme is $v$-verifiable if the client can verify the correctness of the retrieved $x_i$ even when $v \leq k$ servers collude and try to fool the client by sending manipulated data.

Information Retrieval Retrieval

Decentralized Voltage Control with Peer-to-peer Energy Trading in a Distribution Network

no code implementations29 Dec 2022 Chen Feng, Andrew L. Lu, Yihsu Chen

Utilizing distributed renewable and energy storage resources via peer-to-peer (P2P) energy trading has long been touted as a solution to improve energy system's resilience and sustainability.

energy trading Management +1

Robust Collaborative 3D Object Detection in Presence of Pose Errors

1 code implementation14 Nov 2022 Yifan Lu, Quanhao Li, Baoan Liu, Mehrdad Dianati, Chen Feng, Siheng Chen, Yanfeng Wang

Collaborative 3D object detection exploits information exchange among multiple agents to enhance accuracy of object detection in presence of sensor impairments such as occlusion.

3D Object Detection object-detection +1

UNav: An Infrastructure-Independent Vision-Based Navigation System for People with Blindness and Low vision

no code implementations22 Sep 2022 Anbang Yang, Mahya Beheshti, Todd E Hudson, Rajesh Vedanthan, Wachara Riewpaiboon, Pattanasak Mongkolwat, Chen Feng, John-Ross Rizzo

Given a query image taken by an end-user on a mobile application, the pipeline leverages a visual place recognition (VPR) algorithm to find similar images in a reference image database of the target space.

Visual Place Recognition

Self-Supervised Visual Place Recognition by Mining Temporal and Feature Neighborhoods

no code implementations19 Aug 2022 Chao Chen, Xinhao Liu, Xuchu Xu, Yiming Li, Li Ding, Ruoyu Wang, Chen Feng

Inspired by noisy label learning, we propose a novel self-supervised framework named \textit{TF-VPR} that uses temporal neighborhoods and learnable feature neighborhoods to discover unknown spatial neighborhoods.

Data Augmentation Representation Learning +1

Adaptive Soft Contrastive Learning

1 code implementation22 Jul 2022 Chen Feng, Ioannis Patras

Self-supervised learning has recently achieved great success in representation learning without human annotations.

Contrastive Learning Representation Learning +1

Enhancing HDR Video Compression through CNN-based Effective Bit Depth Adaptation

1 code implementation18 Jul 2022 Chen Feng, Zihao Qi, Duolikun Danier, Fan Zhang, Xiaozhong Xu, Shan Liu, David Bull

In this work, we modify the MFRNet network architecture to enable multiple frame processing, and the new network, multi-frame MFRNet, has been integrated into the EBDA framework using two Versatile Video Coding (VVC) host codecs: VTM 16. 2 and the Fraunhofer Versatile Video Encoder (VVenC 1. 4. 0).

Video Compression

Enhancing VVC with Deep Learning based Multi-Frame Post-Processing

no code implementations19 May 2022 Duolikun Danier, Chen Feng, Fan Zhang, David Bull

This paper describes a CNN-based multi-frame post-processing approach based on a perceptually-inspired Generative Adversarial Network architecture, CVEGAN.

Image Compression

Egocentric Prediction of Action Target in 3D

no code implementations CVPR 2022 Yiming Li, Ziang Cao, Andrew Liang, Benjamin Liang, Luoyao Chen, Hang Zhao, Chen Feng

We are interested in anticipating as early as possible the target location of a person's object manipulation action in a 3D workspace from egocentric vision.

An Empirical Study of Low Precision Quantization for TinyML

no code implementations10 Mar 2022 Shaojie Zhuo, Hongyu Chen, Ramchalam Kinattinkara Ramakrishnan, Tommy Chen, Chen Feng, Yicheng Lin, Parker Zhang, Liang Shen

In this study, we focus on post-training quantization (PTQ) algorithms that quantize a model to low-bit (less than 8-bit) precision with only a small set of calibration data and benchmark them on different tinyML use cases.

BIG-bench Machine Learning Model Compression +1

RankDVQA: Deep VQA based on Ranking-inspired Hybrid Training

no code implementations17 Feb 2022 Chen Feng, Duolikun Danier, Fan Zhang, David R. Bull

In recent years, deep learning techniques have shown significant potential for improving video quality assessment (VQA), achieving higher correlation with subjective opinions compared to conventional approaches.

Video Quality Assessment Visual Question Answering (VQA)

V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving

no code implementations17 Feb 2022 Yiming Li, Dekun Ma, Ziyan An, Zixun Wang, Yiqi Zhong, Siheng Chen, Chen Feng

Vehicle-to-everything (V2X) communication techniques enable the collaboration between vehicles and many other entities in the neighboring environment, which could fundamentally improve the perception system for autonomous driving.

Autonomous Driving

SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise

1 code implementation22 Nov 2021 Chen Feng, Georgios Tzimiropoulos, Ioannis Patras

Under this setting, unlike previous methods that often introduce multiple assumptions and lead to complex solutions, we propose a simple, efficient and robust framework named Sample Selection and Relabelling(SSR), that with a minimal number of hyperparameters achieves SOTA results in various conditions.

Learning with noisy labels Self-Supervised Learning +1

Learning Distilled Collaboration Graph for Multi-Agent Perception

2 code implementations NeurIPS 2021 Yiming Li, Shunli Ren, Pengxiang Wu, Siheng Chen, Chen Feng, Wenjun Zhang

Our approach is validated on V2X-Sim 1. 0, a large-scale multi-agent perception dataset that we synthesized using CARLA and SUMO co-simulation.

3D Object Detection Knowledge Distillation +1

NYU-VPR: Long-Term Visual Place Recognition Benchmark with View Direction and Data Anonymization Influences

no code implementations18 Oct 2021 Diwei Sheng, Yuxiang Chai, Xinru Li, Chen Feng, Jianzhe Lin, Claudio Silva, John-Ross Rizzo

Visual place recognition (VPR) is critical in not only localization and mapping for autonomous driving vehicles, but also in assistive navigation for the visually impaired population.

Autonomous Driving Self-Driving Cars +1

Self-supervised Spatial Reasoning on Multi-View Line Drawings

1 code implementation CVPR 2022 Siyuan Xiang, Anbang Yang, Yanfei Xue, Yaoqing Yang, Chen Feng

Based on the fact that self-supervised learning is helpful when a large number of data are available, we propose two self-supervised learning approaches to improve the baseline performance for view consistency reasoning and camera pose reasoning tasks on the SPARE3D dataset.

Binary Classification Contrastive Learning +2

Deep Weakly Supervised Positioning

no code implementations10 Apr 2021 Ruoyu Wang, Xuchu Xu, Li Ding, Yang Huang, Chen Feng

PoseNet can map a photo to the position where it is taken, which is appealing in robotics.

Simultaneous Navigation and Construction Benchmarking Environments

1 code implementation31 Mar 2021 Wenyu Han, Chen Feng, Haoran Wu, Alexander Gao, Armand Jordana, Dong Liu, Lerrel Pinto, Ludovic Righetti

We need intelligent robots for mobile construction, the process of navigating in an environment and modifying its structure according to a geometric design.

Benchmarking Reinforcement Learning (RL) +2

Fooling LiDAR Perception via Adversarial Trajectory Perturbation

1 code implementation ICCV 2021 Yiming Li, Congcong Wen, Felix Juefei-Xu, Chen Feng

LiDAR point clouds collected from a moving vehicle are functions of its trajectories, because the sensor motion needs to be compensated to avoid distortions.

3D Object Detection Autonomous Vehicles +2

AETree: Areal Spatial Data Generation

no code implementations1 Jan 2021 Congcong Wen, Wenyu Han, Hang Zhao, Chen Feng

Areal spatial data represent not only geographical locations but also sizes and shapes of physical objects such as buildings in a city.


Mobile Construction Benchmark

no code implementations1 Jan 2021 Wenyu Han, Chen Feng, Haoran Wu, Alexander Gao, Armand Jordana, Dongdong Liu, Lerrel Pinto, Ludovic Righetti

We need intelligent robots to perform mobile construction, the process of moving in an environment and modifying its geometry according to a design plan.

Siamese Anchor Proposal Network for High-Speed Aerial Tracking

1 code implementation19 Dec 2020 Changhong Fu, Ziang Cao, Yiming Li, Junjie Ye, Chen Feng

In the domain of visual tracking, most deep learning-based trackers highlight the accuracy but casting aside efficiency.

Visual Tracking Vocal Bursts Intensity Prediction

Video Compression with CNN-based Post Processing

no code implementations16 Sep 2020 Fan Zhang, Di Ma, Chen Feng, David R. Bull

In recent years, video compression techniques have been significantly challenged by the rapidly increased demands associated with high quality and immersive video content.

Video Compression

DR^2Track: Towards Real-Time Visual Tracking for UAV via Distractor Repressed Dynamic Regression

1 code implementation10 Aug 2020 Changhong Fu, Fangqiang Ding, Yiming Li, Jin Jin, Chen Feng

By repressing the response of distractors in the regressor learning, we can dynamically and adaptively alter our regression target to leverage the tracking robustness as well as adaptivity.

Real-Time Visual Tracking regression

Automatic Failure Recovery and Re-Initialization for Online UAV Tracking with Joint Scale and Aspect Ratio Optimization

1 code implementation10 Aug 2020 Fangqiang Ding, Changhong Fu, Yiming Li, Jin Jin, Chen Feng

Current unmanned aerial vehicle (UAV) visual tracking algorithms are primarily limited with respect to: (i) the kind of size variation they can deal with, (ii) the implementation speed which hardly meets the real-time requirement.

Translation Visual Tracking

SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings

1 code implementation CVPR 2020 Wenyu Han, Siyuan Xiang, Chenhui Liu, Ruoyu Wang, Chen Feng

Our experiments show that although convolutional networks have achieved superhuman performance in many visual learning tasks, their spatial reasoning performance on SPARE3D tasks is either lower than average human performance or even close to random guesses.

A Robust Speaker Clustering Method Based on Discrete Tied Variational Autoencoder

no code implementations4 Mar 2020 Chen Feng, Jianzong Wang, Tongxu Li, Junqing Peng, Jing Xiao

Recently, the speaker clustering model based on aggregation hierarchy cluster (AHC) is a common method to solve two main problems: no preset category number clustering and fix category number clustering.


Incentive Analysis of Bitcoin-NG, Revisited

no code implementations14 Jan 2020 Jianyu Niu, Ziyu Wang, Fangyu Gai, Chen Feng

First, we propose a new incentive analysis that takes the network capacity into account, showing that Bitcoin-NG can still maintain incentive compatibility against the microblock mining attack even under limited network capacity.

Cryptography and Security Distributed, Parallel, and Cluster Computing

Regularizing Neural Networks via Minimizing Hyperspherical Energy

1 code implementation CVPR 2020 Rongmei Lin, Weiyang Liu, Zhen Liu, Chen Feng, Zhiding Yu, James M. Rehg, Li Xiong, Le Song

Inspired by the Thomson problem in physics where the distribution of multiple propelling electrons on a unit sphere can be modeled via minimizing some potential energy, hyperspherical energy minimization has demonstrated its potential in regularizing neural networks and improving their generalization power.

Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering

no code implementations11 May 2019 Siheng Chen, Chaojing Duan, Yaoqing Yang, Duanshun Li, Chen Feng, Dong Tian

The experimental results show that (1) the proposed networks outperform the state-of-the-art methods in various tasks; (2) a graph topology can be inferred as auxiliary information without specific supervision on graph topology inference; and (3) graph filtering refines the reconstruction, leading to better performances.

3D Point Cloud Reconstruction General Classification +1

Dynamic Origin-Destination Matrix Prediction with Line Graph Neural Networks and Kalman Filter

1 code implementation1 May 2019 Xi Xiong, Kaan Ozbay, Li Jin, Chen Feng

In this paper we propose a novel O-D prediction framework combining heterogeneous prediction in graph neural networks and Kalman filter to recognize spatial and temporal patterns simultaneously.

Real-time Soft Body 3D Proprioception via Deep Vision-based Sensing

1 code implementation8 Apr 2019 Ruoyu Wang, Shiheng Wang, Songyu Du, Erdong Xiao, Wenzhen Yuan, Chen Feng

Soft bodies made from flexible and deformable materials are popular in many robotics applications, but their proprioceptive sensing has been a long-standing challenge.


Low Power Inference for On-Device Visual Recognition with a Quantization-Friendly Solution

no code implementations12 Mar 2019 Chen Feng, Tao Sheng, Zhiyu Liang, Shaojie Zhuo, Xiaopeng Zhang, Liang Shen, Matthew Ardi, Alexander C. Berg, Yiran Chen, Bo Chen, Kent Gauen, Yung-Hsiang Lu

The IEEE Low-Power Image Recognition Challenge (LPIRC) is an annual competition started in 2015 that encourages joint hardware and software solutions for computer vision systems with low latency and power.


DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds

1 code implementation CVPR 2019 Li Ding, Chen Feng

We propose DeepMapping, a novel registration framework using deep neural networks (DNNs) as auxiliary functions to align multiple point clouds from scratch to a globally consistent frame.

Point Cloud Registration

Primitive Fitting Using Deep Boundary Aware Geometric Segmentation

1 code implementation3 Oct 2018 Duanshun Li, Chen Feng

To identify and fit geometric primitives (e. g., planes, spheres, cylinders, cones) in a noisy point cloud is a challenging yet beneficial task for fields such as robotics and reverse engineering.

Semantic Segmentation

Simultaneous Edge Alignment and Learning

3 code implementations ECCV 2018 Zhiding Yu, Weiyang Liu, Yang Zou, Chen Feng, Srikumar Ramalingam, B. V. K. Vijaya Kumar, Jan Kautz

Edge detection is among the most fundamental vision problems for its role in perceptual grouping and its wide applications.

Edge Detection Representation Learning

VLASE: Vehicle Localization by Aggregating Semantic Edges

1 code implementation6 Jul 2018 Xin Yu, Sagar Chaturvedi, Chen Feng, Yuichi Taguchi, Teng-Yok Lee, Clinton Fernandes, Srikumar Ramalingam

In this paper, we propose VLASE, a framework to use semantic edge features from images to achieve on-road localization.

Image Retrieval Retrieval

A Quantization-Friendly Separable Convolution for MobileNets

no code implementations22 Mar 2018 Tao Sheng, Chen Feng, Shaojie Zhuo, Xiaopeng Zhang, Liang Shen, Mickey Aleksic

As deep learning (DL) is being rapidly pushed to edge computing, researchers invented various ways to make inference computation more efficient on mobile/IoT devices, such as network pruning, parameter compression, and etc.

Edge-computing Image Classification +2

FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation

3 code implementations CVPR 2018 Yaoqing Yang, Chen Feng, Yiru Shen, Dong Tian

Recent deep networks that directly handle points in a point set, e. g., PointNet, have been state-of-the-art for supervised learning tasks on point clouds such as classification and segmentation.

3D Point Cloud Linear Classification General Classification +1

Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling

1 code implementation CVPR 2018 Yiru Shen, Chen Feng, Yaoqing Yang, Dong Tian

Unlike on images, semantic learning on 3D point clouds using a deep network is challenging due to the naturally unordered data structure.

Point Cloud Registration

CASENet: Deep Category-Aware Semantic Edge Detection

11 code implementations CVPR 2017 Zhiding Yu, Chen Feng, Ming-Yu Liu, Srikumar Ramalingam

To this end, we propose a novel end-to-end deep semantic edge learning architecture based on ResNet and a new skip-layer architecture where category-wise edge activations at the top convolution layer share and are fused with the same set of bottom layer features.

Edge Detection Object Proposal Generation +1

Fast Resampling of 3D Point Clouds via Graphs

no code implementations11 Feb 2017 Siheng Chen, Dong Tian, Chen Feng, Anthony Vetro, Jelena Kovačević

We use a general feature-extraction operator to represent application-dependent features and propose a general reconstruction error to evaluate the quality of resampling.

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