Search Results for author: Yifan Zhang

Found 142 papers, 62 papers with code

Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition

1 code implementation ECCV 2020 Ke Cheng, Yifan Zhang, Congqi Cao, Lei Shi, Jian Cheng, Hanqing Lu

Nevertheless, how to efficiently model the spatial-temporal skeleton graph without introducing extra computation burden is a challenging problem for industrial deployment.

Action Recognition Skeleton Based Action Recognition

COVID-19 in Bulgarian Social Media: Factuality, Harmfulness, Propaganda, and Framing

1 code implementation RANLP 2021 Preslav Nakov, Firoj Alam, Shaden Shaar, Giovanni Da San Martino, Yifan Zhang

With the emergence of the COVID-19 pandemic, the political and the medical aspects of disinformation merged as the problem got elevated to a whole new level to become the first global infodemic.

Persuasion in Networks: Can the Sender Do Better than Using Public Signals?

no code implementations29 Apr 2024 Yifan Zhang

Political and advertising campaigns increasingly exploit social networks to spread information and persuade people.

Three-Dimension Collision-Free Trajectory Planning of UAVs Based on ADS-B Information in Low-Altitude Urban Airspace

no code implementations29 Apr 2024 Chao Dong, Yifan Zhang, Ziye Jia, Yiyang Liao, Lei Zhang, Qihui Wu

Consequently, we leverage ADS-B for surveillance and information broadcasting, and divide the aerial airspace into multiple sub-airspaces to improve flight safety in UAV trajectory planning.

Trajectory Planning

A Comprehensive Evaluation on Event Reasoning of Large Language Models

1 code implementation26 Apr 2024 Zhengwei Tao, Zhi Jin, Yifan Zhang, Xiancai Chen, Xiaoying Bai, Yue Fang, Haiyan Zhao, Jia Li, Chongyang Tao

Based on these findings, we introduce two methods to guide the LLMs to utilize the event schema knowledge.

PATE-TripleGAN: Privacy-Preserving Image Synthesis with Gaussian Differential Privacy

no code implementations19 Apr 2024 Zepeng Jiang, Weiwei Ni, Yifan Zhang

This algorithm allows the model to retain gradient information more effectively while ensuring privacy protection, thereby enhancing the model's utility.

Image Generation Privacy Preserving

MEEL: Multi-Modal Event Evolution Learning

1 code implementation16 Apr 2024 Zhengwei Tao, Zhi Jin, Junqiang Huang, Xiancai Chen, Xiaoying Bai, Haiyan Zhao, Yifan Zhang, Chongyang Tao

Finally, we observe that models trained in this way are still struggling to fully comprehend event evolution.

Low-cost adaptive obstacle avoidance trajectory control for express delivery drone

no code implementations29 Mar 2024 Yanhui Zhang, Caisheng Wei, Yifan Zhang, Congcong Tian, Weifang Chen

This paper studies quadcopters obstacle avoidance trajectory control (OATC) problem for express delivery.

Practical Applications of Advanced Cloud Services and Generative AI Systems in Medical Image Analysis

no code implementations26 Mar 2024 Jingyu Xu, Binbin Wu, Jiaxin Huang, Yulu Gong, Yifan Zhang, Bo Liu

With the explosive growth and diversification of medical data, as well as the continuous improvement of medical needs and challenges, artificial intelligence technology is playing an increasingly important role in the medical field.

Anomaly Detection Image-to-Image Translation

Dynamic Resource Allocation for Virtual Machine Migration Optimization using Machine Learning

no code implementations20 Mar 2024 Yulu Gong, Jiaxin Huang, Bo Liu, Jingyu Xu, Binbin Wu, Yifan Zhang

Overall, the paragraph effectively communicates the importance of machine learning technology in addressing resource allocation and virtual machine migration challenges in cloud computing.

Cloud Computing

Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting

no code implementations18 Mar 2024 Mingkui Tan, Guohao Chen, Jiaxiang Wu, Yifan Zhang, Yaofo Chen, Peilin Zhao, Shuaicheng Niu

To tackle this, we further propose EATA with Calibration (EATA-C) to separately exploit the reducible model uncertainty and the inherent data uncertainty for calibrated TTA.

Image Classification Semantic Segmentation +1

EyeTrans: Merging Human and Machine Attention for Neural Code Summarization

1 code implementation21 Feb 2024 Yifan Zhang, Jiliang Li, Zachary Karas, Aakash Bansal, Toby Jia-Jun Li, Collin McMillan, Kevin Leach, Yu Huang

Neural code summarization leverages deep learning models to automatically generate brief natural language summaries of code snippets.

Code Summarization

Autonomous Data Selection with Language Models for Mathematical Texts

2 code implementations12 Feb 2024 Yifan Zhang, Yifan Luo, Yang Yuan, Andrew Chi-Chih Yao

Our method showcases a 2 times increase in pretraining token efficiency compared to state-of-the-art baselines, underscoring the potential of our approach in enhancing models' mathematical reasoning capabilities.

Continual Pretraining GSM8K +3

The Fragile Nature of Road Transportation Systems

no code implementations1 Feb 2024 Linghang Sun, Yifan Zhang, Cristian Axenie, Margherita Grossi, Anastasios Kouvelas, Michail A. Makridis

The continuous increase in traffic demand presents a substantial challenge to the optimal operation of urban road networks and the efficiency of traffic control strategies.

A Time-varying Shockwave Speed Model for Trajectory Reconstruction using Lagrangian and Eulerian Observations

no code implementations29 Jan 2024 Yifan Zhang, Anastasios Kouvelas, Michail A. Makridis

The calibrated shockwave speed of the CV is then utilized for trajectory reconstruction of other non-connected vehicles based on shockwave theory.

Cross-Space Adaptive Filter: Integrating Graph Topology and Node Attributes for Alleviating the Over-smoothing Problem

1 code implementation26 Jan 2024 Chen Huang, Haoyang Li, Yifan Zhang, Wenqiang Lei, Jiancheng Lv

To this end, various methods have been proposed to create an adaptive filter by incorporating an extra filter (e. g., a high-pass filter) extracted from the graph topology.

Attribute Node Classification

Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration

no code implementations23 Jan 2024 Yifan Zhang, Siyu Ren, Junhui Hou, Jinjian Wu, Guangming Shi

First, we propose the learnable transformation alignment to bridge the domain gap between image and point cloud data, converting features into a unified representation space for effective comparison and matching.

3D Semantic Segmentation Autonomous Driving +4

Augmenting Math Word Problems via Iterative Question Composing

1 code implementation17 Jan 2024 Haoxiong Liu, Yifan Zhang, Yifan Luo, Andrew Chi-Chih Yao

The MMIQC dataset is available on the HuggingFace hub at https://huggingface. co/datasets/Vivacem/MMIQC.

Ranked #41 on Math Word Problem Solving on MATH (using extra training data)

Math Math Word Problem Solving

MicroNAS: Zero-Shot Neural Architecture Search for MCUs

no code implementations17 Jan 2024 Ye Qiao, Haocheng Xu, Yifan Zhang, Sitao Huang

Neural Architecture Search (NAS) effectively discovers new Convolutional Neural Network (CNN) architectures, particularly for accuracy optimization.

Edge-computing Neural Architecture Search

Segment Any Events via Weighted Adaptation of Pivotal Tokens

1 code implementation24 Dec 2023 Zhiwen Chen, Zhiyu Zhu, Yifan Zhang, Junhui Hou, Guangming Shi, Jinjian Wu

One pivotal issue at the heart of this endeavor is the precise alignment and calibration of embeddings derived from event-centric data such that they harmoniously coincide with those originating from RGB imagery.

Event-based Object Segmentation

Model-free Test Time Adaptation for Out-Of-Distribution Detection

no code implementations28 Nov 2023 Yifan Zhang, Xue Wang, Tian Zhou, Kun Yuan, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan

We demonstrate the effectiveness of \abbr through comprehensive experiments on multiple OOD detection benchmarks, extensive empirical studies show that \abbr significantly improves the performance of OOD detection over state-of-the-art methods.

Decision Making Out-of-Distribution Detection +2

CMFDFormer: Transformer-based Copy-Move Forgery Detection with Continual Learning

no code implementations22 Nov 2023 Yaqi Liu, Chao Xia, Song Xiao, Qingxiao Guan, Wenqian Dong, Yifan Zhang, Nenghai Yu

In this paper, we propose a Transformer-style copy-move forgery detection network named as CMFDFormer, and provide a novel PCSD (Pooled Cube and Strip Distillation) continual learning framework to help CMFDFormer handle new tasks.

Continual Learning

Meta Prompting for AI Systems

1 code implementation20 Nov 2023 Yifan Zhang, Yang Yuan, Andrew Chi-Chih Yao

In this work, we present a comprehensive study of Meta Prompting (MP), an innovative technique reshaping the utilization of language models (LMs) and AI systems in problem-solving and data interaction.

Data Interaction GSM8K +2

Deep Tensor Network

no code implementations18 Nov 2023 Yifan Zhang

In this paper, we delve into the foundational principles of tensor categories, harnessing the universal property of the tensor product to pioneer novel methodologies in deep network architectures.

Computational Efficiency

BClean: A Bayesian Data Cleaning System

1 code implementation11 Nov 2023 Jianbin Qin, Sifan Huang, Yaoshu Wang, Jing Zhu, Yifan Zhang, Yukai Miao, Rui Mao, Makoto Onizuka, Chuan Xiao

By evaluating on both real-world and synthetic datasets, we demonstrate that BClean is capable of achieving an F-measure of up to 0. 9 in data cleaning, outperforming existing Bayesian methods by 2% and other data cleaning methods by 15%.

Bayesian Inference graph partitioning

Covering Number of Real Algebraic Varieties and Beyond: Improved Bounds and Applications

no code implementations9 Nov 2023 Yifan Zhang, Joe Kileel

Covering numbers are a powerful tool used in the development of approximation algorithms, randomized dimension reduction methods, smoothed complexity analysis, and others.

Dimensionality Reduction

Robustness May be More Brittle than We Think under Different Degrees of Distribution Shifts

no code implementations10 Oct 2023 Kaican Li, Yifan Zhang, Lanqing Hong, Zhenguo Li, Nevin L. Zhang

This indicates that while pre-trained representations may help improve downstream in-distribution performance, they could have minimal or even adverse effects on generalization in certain OOD scenarios of the downstream task if not used properly.

A Critical Look at Classic Test-Time Adaptation Methods in Semantic Segmentation

no code implementations9 Oct 2023 Chang'an Yi, Haotian Chen, Yifan Zhang, Yonghui Xu, Lizhen Cui

This pronounced emphasis on classification might lead numerous newcomers and engineers to mistakenly assume that classic TTA methods designed for classification can be directly applied to segmentation.

Classification Segmentation +2

Implicit Concept Removal of Diffusion Models

no code implementations9 Oct 2023 Zhili Liu, Kai Chen, Yifan Zhang, Jianhua Han, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-yan Yeung, James Kwok

To address this, we utilize the intrinsic geometric characteristics of implicit concepts and present the Geom-Erasing, a novel concept removal method based on geometric-driven control.

Can pre-trained models assist in dataset distillation?

1 code implementation5 Oct 2023 Yao Lu, Xuguang Chen, Yuchen Zhang, Jianyang Gu, Tianle Zhang, Yifan Zhang, Xiaoniu Yang, Qi Xuan, Kai Wang, Yang You

Dataset Distillation (DD) is a prominent technique that encapsulates knowledge from a large-scale original dataset into a small synthetic dataset for efficient training.

Information Flow in Self-Supervised Learning

2 code implementations29 Sep 2023 Zhiquan Tan, Jingqin Yang, Weiran Huang, Yang Yuan, Yifan Zhang

In this paper, we provide a comprehensive toolbox for understanding and enhancing self-supervised learning (SSL) methods through the lens of matrix information theory.

Self-Supervised Learning

A Fine-Grained Image Description Generation Method Based on Joint Objectives

no code implementations2 Sep 2023 Yifan Zhang, Chunzhen Lin, Donglin Cao, Dazhen Lin

The goal of fine-grained image description generation techniques is to learn detailed information from images and simulate human-like descriptions that provide coherent and comprehensive textual details about the image content.

Object

Illumination Distillation Framework for Nighttime Person Re-Identification and A New Benchmark

1 code implementation31 Aug 2023 Andong Lu, Zhang Zhang, Yan Huang, Yifan Zhang, Chenglong Li, Jin Tang, Liang Wang

The illumination enhancement branch first estimates an enhanced image from the nighttime image using a nonlinear curve mapping method and then extracts the enhanced features.

Person Re-Identification

FPTQ: Fine-grained Post-Training Quantization for Large Language Models

no code implementations30 Aug 2023 Qingyuan Li, Yifan Zhang, Liang Li, Peng Yao, Bo Zhang, Xiangxiang Chu, Yerui Sun, Li Du, Yuchen Xie

In this study, we propose a novel W4A8 post-training quantization method for the available open-sourced LLMs, which combines the advantages of both two recipes.

Quantization

Dataset Quantization

1 code implementation ICCV 2023 Daquan Zhou, Kai Wang, Jianyang Gu, Xiangyu Peng, Dongze Lian, Yifan Zhang, Yang You, Jiashi Feng

Extensive experiments demonstrate that DQ is able to generate condensed small datasets for training unseen network architectures with state-of-the-art compression ratios for lossless model training.

object-detection Object Detection +2

Cumulative Reasoning with Large Language Models

1 code implementation8 Aug 2023 Yifan Zhang, Jingqin Yang, Yang Yuan, Andrew Chi-Chih Yao

We demonstrate CR's superiority through several complex reasoning tasks: it outperforms existing methods in logical inference tasks with up to a 9. 3% improvement, achieving 98. 04% accuracy on the curated FOLIO wiki dataset.

Decision Making Logical Reasoning +2

GeoGPT: Understanding and Processing Geospatial Tasks through An Autonomous GPT

no code implementations16 Jul 2023 Yifan Zhang, Cheng Wei, Shangyou Wu, Zhengting He, Wenhao Yu

Though limited cases are presented in this paper, GeoGPT can be further extended to various tasks by equipping with more GIS tools, and we think the paradigm of "foundational plus professional" implied in GeoGPT provides an effective way to develop next-generation GIS in this era of large foundation models.

Impact of UAVs Equipped with ADS-B on the Civil Aviation Monitoring System

no code implementations4 Jul 2023 Yiyang Liao, Lei Zhang, Ziye Jia, Chao Dong, Yifan Zhang, Qihui Wu, Huiling Hu, Bin Wang

However, due to the limited frequency of ADS-B technique, UAVs equipped with ADS-B devices result in the loss of packets to both UAVs and civil aviation.

Blocking Position

Spatial-Temporal Enhanced Transformer Towards Multi-Frame 3D Object Detection

1 code implementation1 Jul 2023 Yifan Zhang, Zhiyu Zhu, Junhui Hou, Dapeng Wu

Specifically, to model the inter-object spatial interaction and complex temporal dependencies, we introduce the spatial-temporal graph attention network, which represents queries as nodes in a graph and enables effective modeling of object interactions within a social context.

3D Object Detection Graph Attention +2

CARMA: Context-Aware Runtime Reconfiguration for Energy-Efficient Sensor Fusion

no code implementations27 Jun 2023 Yifan Zhang, Arnav Vaibhav Malawade, Xiaofang Zhang, Yuhui Li, DongHwan Seong, Mohammad Abdullah Al Faruque, Sitao Huang

Autonomous systems (AS) are systems that can adapt and change their behavior in response to unanticipated events and include systems such as aerial drones, autonomous vehicles, and ground/aquatic robots.

Autonomous Vehicles Sensor Fusion

SplatFlow: Learning Multi-frame Optical Flow via Splatting

1 code implementation15 Jun 2023 Bo wang, Yifan Zhang, Jian Li, Yang Yu, Zhenping Sun, Li Liu, Dewen Hu

The occlusion problem remains a crucial challenge in optical flow estimation (OFE).

Optical Flow Estimation

TOFG: A Unified and Fine-Grained Environment Representation in Autonomous Driving

no code implementations31 May 2023 Zihao Wen, Yifan Zhang, Xinhong Chen, JianPing Wang

Due to the heterogeneity of the map data and trajectory data, many data-driven models for trajectory prediction and motion planning extract vehicle-to-vehicle and vehicle-to-lane interactions in a separate and sequential manner.

Autonomous Driving Graph Attention +2

Matrix Information Theory for Self-Supervised Learning

3 code implementations27 May 2023 Yifan Zhang, Zhiquan Tan, Jingqin Yang, Weiran Huang, Yang Yuan

Inspired by this framework, we introduce Matrix-SSL, a novel approach that leverages matrix information theory to interpret the maximum entropy encoding loss as matrix uniformity loss.

Contrastive Learning GSM8K +5

Imbalance-Agnostic Source-Free Domain Adaptation via Avatar Prototype Alignment

no code implementations22 May 2023 Hongbin Lin, Mingkui Tan, Yifan Zhang, Zhen Qiu, Shuaicheng Niu, Dong Liu, Qing Du, Yanxia Liu

To address this issue, we study a more practical SF-UDA task, termed imbalance-agnostic SF-UDA, where the class distributions of both the unseen source domain and unlabeled target domain are unknown and could be arbitrarily skewed.

Pseudo Label Source-Free Domain Adaptation +1

RelationMatch: Matching In-batch Relationships for Semi-supervised Learning

1 code implementation17 May 2023 Yifan Zhang, Jingqin Yang, Zhiquan Tan, Yang Yuan

Semi-supervised learning has achieved notable success by leveraging very few labeled data and exploiting the wealth of information derived from unlabeled data.

Semi-Supervised Image Classification

Model-Contrastive Federated Domain Adaptation

no code implementations7 May 2023 Chang'an Yi, Haotian Chen, Yonghui Xu, Yifan Zhang

Federated domain adaptation (FDA) aims to collaboratively transfer knowledge from source clients (domains) to the related but different target client, without communicating the local data of any client.

Contrastive Learning Domain Adaptation +1

SEAL: Simultaneous Label Hierarchy Exploration And Learning

1 code implementation26 Apr 2023 Zhiquan Tan, ZiHao Wang, Yifan Zhang

Label hierarchy is an important source of external knowledge that can enhance classification performance.

Contrastive Learning Is Spectral Clustering On Similarity Graph

1 code implementation27 Mar 2023 Zhiquan Tan, Yifan Zhang, Jingqin Yang, Yang Yuan

Contrastive learning is a powerful self-supervised learning method, but we have a limited theoretical understanding of how it works and why it works.

Clustering Contrastive Learning +1

Disentangling Writer and Character Styles for Handwriting Generation

1 code implementation CVPR 2023 Gang Dai, Yifan Zhang, Qingfeng Wang, Qing Du, Zhuliang Yu, Zhuoman Liu, Shuangping Huang

In light of this, we propose to disentangle the style representations at both writer and character levels from individual handwritings to synthesize realistic stylized online handwritten characters.

Handwriting generation

Towards Stable Test-Time Adaptation in Dynamic Wild World

1 code implementation24 Feb 2023 Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Zhiquan Wen, Yaofo Chen, Peilin Zhao, Mingkui Tan

In this paper, we investigate the unstable reasons and find that the batch norm layer is a crucial factor hindering TTA stability.

Test-time Adaptation

Unleash the Potential of Image Branch for Cross-modal 3D Object Detection

1 code implementation NeurIPS 2023 Yifan Zhang, Qijian Zhang, Junhui Hou, Yixuan Yuan, Guoliang Xing

To achieve reliable and precise scene understanding, autonomous vehicles typically incorporate multiple sensing modalities to capitalize on their complementary attributes.

3D Object Detection Autonomous Vehicles +2

A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks

1 code implementation20 Dec 2022 Yifan Zhang, Junhui Hou, Yixuan Yuan

Specifically, we extend three distinct adversarial attacks to the 3D object detection task, benchmarking the robustness of state-of-the-art LiDAR-based 3D object detectors against attacks on the KITTI and Waymo datasets.

3D Object Detection Benchmarking +2

Expanding Small-Scale Datasets with Guided Imagination

1 code implementation NeurIPS 2023 Yifan Zhang, Daquan Zhou, Bryan Hooi, Kai Wang, Jiashi Feng

Specifically, GIF conducts data imagination by optimizing the latent features of the seed data in the semantically meaningful space of the prior model, resulting in the creation of photo-realistic images with new content.

Moment Estimation for Nonparametric Mixture Models Through Implicit Tensor Decomposition

1 code implementation25 Oct 2022 Yifan Zhang, Joe Kileel

We present an alternating least squares type numerical optimization scheme to estimate conditionally-independent mixture models in $\mathbb{R}^n$, without parameterizing the distributions.

Tensor Decomposition

Dual-Curriculum Teacher for Domain-Inconsistent Object Detection in Autonomous Driving

no code implementations17 Oct 2022 Longhui Yu, Yifan Zhang, Lanqing Hong, Fei Chen, Zhenguo Li

Specifically, DucTeacher consists of two curriculums, i. e., (1) domain evolving curriculum seeks to learn from the data progressively to handle data distribution discrepancy by estimating the similarity between domains, and (2) distribution matching curriculum seeks to estimate the class distribution for each unlabeled domain to handle class distribution shifts.

Autonomous Driving object-detection +2

Pre-Training Representations of Binary Code Using Contrastive Learning

no code implementations11 Oct 2022 Yifan Zhang, Chen Huang, Yueke Zhang, Kevin Cao, Scott Thomas Andersen, Huajie Shao, Kevin Leach, Yu Huang

To the best of our knowledge, COMBO is the first language representation model that incorporates source code, binary code, and comments into contrastive code representation learning and unifies multiple tasks for binary code analysis.

Computer Security Contrastive Learning +2

Leveraging Artificial Intelligence on Binary Code Comprehension

no code implementations11 Oct 2022 Yifan Zhang

We propose to develop Artificial Intelligence (AI) models that aid human comprehension of binary code.

Compiler Optimization Malware Analysis

Recurrent LSTM-based UAV Trajectory Prediction with ADS-B Information

no code implementations1 Sep 2022 Yifan Zhang, Ziye Jia, Chao Dong, Yuntian Liu, Lei Zhang, Qihui Wu

It is noted that the recurrent neural network (RNN) is available for the UAV trajectory prediction, in which the long short-term memory (LSTM) is specialized in dealing with the time-series data.

Time Series Analysis Trajectory Prediction

Multi-Scale Multi-Target Domain Adaptation for Angle Closure Classification

no code implementations25 Aug 2022 Zhen Qiu, Yifan Zhang, Fei Li, Xiulan Zhang, Yanwu Xu, Mingkui Tan

Based on these domain-invariant features at different scales, the deep model trained on the source domain is able to classify angle closure on multiple target domains even without any annotations in these domains.

Domain Adaptation Multi-target Domain Adaptation

Quantized Adaptive Subgradient Algorithms and Their Applications

no code implementations11 Aug 2022 Ke Xu, Jianqiao Wangni, Yifan Zhang, Deheng Ye, Jiaxiang Wu, Peilin Zhao

Therefore, a threshold quantization strategy with a relatively small error is adopted in QCMD adagrad and QRDA adagrad to improve the signal-to-noise ratio and preserve the sparsity of the model.

Quantization

CTooth+: A Large-scale Dental Cone Beam Computed Tomography Dataset and Benchmark for Tooth Volume Segmentation

1 code implementation2 Aug 2022 Weiwei Cui, Yaqi Wang, Yilong Li, Dan Song, Xingyong Zuo, Jiaojiao Wang, Yifan Zhang, Huiyu Zhou, Bung san Chong, Liaoyuan Zeng, Qianni Zhang

This work provides a new benchmark for the tooth volume segmentation task, and the experiment can serve as the baseline for future AI-based dental imaging research and clinical application development.

Active Learning Segmentation

Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation

1 code implementation22 Jul 2022 Hongbin Lin, Yifan Zhang, Zhen Qiu, Shuaicheng Niu, Chuang Gan, Yanxia Liu, Mingkui Tan

2) Prototype-based alignment and replay: based on the identified label prototypes, we align both domains and enforce the model to retain previous knowledge.

Unsupervised Domain Adaptation

Unsupervised Visual Representation Learning by Synchronous Momentum Grouping

1 code implementation13 Jul 2022 Bo Pang, Yifan Zhang, Yaoyi Li, Jia Cai, Cewu Lu

In this paper, we propose a genuine group-level contrastive visual representation learning method whose linear evaluation performance on ImageNet surpasses the vanilla supervised learning.

Clustering Contrastive Learning +3

GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation

1 code implementation6 Jul 2022 Yifan Zhang, Qijian Zhang, Zhiyu Zhu, Junhui Hou, Yixuan Yuan

The label uncertainty generated by GLENet is a plug-and-play module and can be conveniently integrated into existing deep 3D detectors to build probabilistic detectors and supervise the learning of the localization uncertainty.

3D Object Detection

PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient

1 code implementation5 Jul 2022 Weihan Cao, Yifan Zhang, Jianfei Gao, Anda Cheng, Ke Cheng, Jian Cheng

First, the difference in feature magnitude between the teacher and the student could enforce overly strict constraints on the student.

Knowledge Distillation object-detection +1

Efficient Test-Time Model Adaptation without Forgetting

1 code implementation6 Apr 2022 Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Yaofo Chen, Shijian Zheng, Peilin Zhao, Mingkui Tan

Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w. r. t.

Test-time Adaptation

Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds

1 code implementation CVPR 2022 Yifan Zhang, Qingyong Hu, Guoquan Xu, Yanxin Ma, Jianwei Wan, Yulan Guo

To reduce the memory and computational cost, existing point-based pipelines usually adopt task-agnostic random sampling or farthest point sampling to progressively downsample input point clouds, despite the fact that not all points are equally important to the task of object detection.

Object object-detection +1

Boost Test-Time Performance with Closed-Loop Inference

no code implementations21 Mar 2022 Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Guanghui Xu, Haokun Li, Peilin Zhao, Junzhou Huang, YaoWei Wang, Mingkui Tan

Motivated by this, we propose to predict those hard-classified test samples in a looped manner to boost the model performance.

Auxiliary Learning

QCRI's COVID-19 Disinformation Detector: A System to Fight the COVID-19 Infodemic in Social Media

no code implementations8 Mar 2022 Preslav Nakov, Firoj Alam, Yifan Zhang, Animesh Prakash, Fahim Dalvi

Fighting the ongoing COVID-19 infodemic has been declared as one of the most important focus areas by the World Health Organization since the onset of the COVID-19 pandemic.

A Generative Car-following Model Conditioned On Driving Styles

no code implementations10 Dec 2021 Yifan Zhang, Xinhong Chen, JianPing Wang, Zuduo Zheng, Kui Wu

Car-following (CF) modeling, an essential component in simulating human CF behaviors, has attracted increasing research interest in the past decades.

Adaptive Channel Encoding Transformer for Point Cloud Analysis

no code implementations5 Dec 2021 Guoquan Xu, Hezhi Cao, Yifan Zhang, Yanxin Ma, Jianwei Wan, Ke Xu

Transformer plays an increasingly important role in various computer vision areas and remarkable achievements have also been made in point cloud analysis.

Point Cloud Classification

Adaptive Channel Encoding for Point Cloud Analysis

no code implementations5 Dec 2021 Guoquan Xu, Hezhi Cao, Yifan Zhang, Jianwei Wan, Ke Xu, Yanxin Ma

Attention mechanism plays a more and more important role in point cloud analysis and channel attention is one of the hotspots.

Lightweight Transformer Backbone for Medical Object Detection

no code implementations22 Nov 2021 Yifan Zhang, Haoyu Dong, Nicholas Konz, Hanxue Gu, Maciej A. Mazurowski

Specifically, we propose a novel modification of visual transformer (ViT) on image feature patches to connect the feature patches of a tumor with healthy backgrounds of breast images and form a more robust backbone for tumor detection.

Lesion Detection Medical Object Detection +2

Detecting and Identifying Optical Signal Attacks on Autonomous Driving Systems

no code implementations20 Oct 2021 Jindi Zhang, Yifan Zhang, Kejie Lu, JianPing Wang, Kui Wu, Xiaohua Jia, Bin Liu

In our study, we use real data sets and the state-of-the-art machine learning model to evaluate our attack detection scheme and the results confirm the effectiveness of our detection method.

Autonomous Driving object-detection +1

Deep Long-Tailed Learning: A Survey

1 code implementation9 Oct 2021 Yifan Zhang, Bingyi Kang, Bryan Hooi, Shuicheng Yan, Jiashi Feng

Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-tailed class distribution.

Generalizable Person Re-identification Without Demographics

no code implementations29 Sep 2021 Yifan Zhang, Feng Li, Zhang Zhang, Liang Wang, DaCheng Tao, Tieniu Tan

However, the convex condition of KL DRO may not hold for overparameterized neural networks, such that applying KL DRO often fails to generalize under distribution shifts in real scenarios.

Generalizable Person Re-identification

How Well Does Self-Supervised Pre-Training Perform with Streaming ImageNet?

no code implementations NeurIPS Workshop ImageNet_PPF 2021 Dapeng Hu, Shipeng Yan, Qizhengqiu Lu, Lanqing Hong, Hailin Hu, Yifan Zhang, Zhenguo Li, Xinchao Wang, Jiashi Feng

Prior works on self-supervised pre-training focus on the joint training scenario, where massive unlabeled data are assumed to be given as input all at once, and only then is a learner trained.

Self-Supervised Learning

A Second Pandemic? Analysis of Fake News About COVID-19 Vaccines in Qatar

no code implementations RANLP 2021 Preslav Nakov, Firoj Alam, Shaden Shaar, Giovanni Da San Martino, Yifan Zhang

While COVID-19 vaccines are finally becoming widely available, a second pandemic that revolves around the circulation of anti-vaxxer fake news may hinder efforts to recover from the first one.

Dual-Neighborhood Deep Fusion Network for Point Cloud Analysis

no code implementations20 Aug 2021 Guoquan Xu, Hezhi Cao, Yifan Zhang, Jianwei Wan, Ke Xu, Yanxin Ma

To handle this prob-lem, a feature representation learning method, named Dual-Neighborhood Deep Fusion Network (DNDFN), is proposed to serve as an improved point cloud encoder for the task of non-idealized point cloud classification.

3D Point Cloud Classification Classification +2

Opinion Prediction with User Fingerprinting

1 code implementation RANLP 2021 Kishore Tumarada, Yifan Zhang, Fan Yang, Eduard Dragut, Omprakash Gnawali, Arjun Mukherjee

Experimental results show novel insights that were previously unknown such as better predictions for an increase in dynamic history length, the impact of the nature of the article on performance, thereby laying the foundation for further research.

Sentiment Analysis Time Series +1

Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition

2 code implementations20 Jul 2021 Yifan Zhang, Bryan Hooi, Lanqing Hong, Jiashi Feng

Existing long-tailed recognition methods, aiming to train class-balanced models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution.

Image Classification Long-tail Learning

AdaXpert: Adapting Neural Architecture for Growing Data

1 code implementation1 Jul 2021 Shuaicheng Niu, Jiaxiang Wu, Guanghui Xu, Yifan Zhang, Yong Guo, Peilin Zhao, Peng Wang, Mingkui Tan

To address this, we present a neural architecture adaptation method, namely Adaptation eXpert (AdaXpert), to efficiently adjust previous architectures on the growing data.

Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation

1 code implementation18 Jun 2021 Zhen Qiu, Yifan Zhang, Hongbin Lin, Shuaicheng Niu, Yanxia Liu, Qing Du, Mingkui Tan

(2) prototype adaptation: based on the generated source prototypes and target pseudo labels, we develop a new robust contrastive prototype adaptation strategy to align each pseudo-labeled target data to the corresponding source prototypes.

Contrastive Learning Source-Free Domain Adaptation +1

No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data

1 code implementation NeurIPS 2021 Mi Luo, Fei Chen, Dapeng Hu, Yifan Zhang, Jian Liang, Jiashi Feng

Motivated by the above findings, we propose a novel and simple algorithm called Classifier Calibration with Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated gaussian mixture model.

Classifier calibration Federated Learning

AGMB-Transformer: Anatomy-Guided Multi-Branch Transformer Network for Automated Evaluation of Root Canal Therapy

1 code implementation2 May 2021 Yunxiang Li, Guodong Zeng, Yifan Zhang, Jun Wang, Qianni Zhang, Qun Jin, Lingling Sun, Qisi Lian, Neng Xia, Ruizi Peng, Kai Tang, Yaqi Wang, Shuai Wang

Accurate evaluation of the treatment result on X-ray images is a significant and challenging step in root canal therapy since the incorrect interpretation of the therapy results will hamper timely follow-up which is crucial to the patients' treatment outcome.

Anatomy General Classification

How Well Does Self-Supervised Pre-Training Perform with Streaming Data?

no code implementations ICLR 2022 Dapeng Hu, Shipeng Yan, Qizhengqiu Lu, Lanqing Hong, Hailin Hu, Yifan Zhang, Zhenguo Li, Xinchao Wang, Jiashi Feng

Prior works on self-supervised pre-training focus on the joint training scenario, where massive unlabeled data are assumed to be given as input all at once, and only then is a learner trained.

Representation Learning Self-Supervised Learning

AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition

no code implementations ICCV 2021 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

Existing methods for skeleton-based action recognition mainly focus on improving the recognition accuracy, whereas the efficiency of the model is rarely considered.

Action Recognition Skeleton Based Action Recognition

Efficient Spatialtemporal Context Modeling for Action Recognition

no code implementations20 Mar 2021 Congqi Cao, Yue Lu, Yifan Zhang, Dongmei Jiang, Yanning Zhang

Inspired from 2D criss-cross attention used in segmentation task, we propose a recurrent 3D criss-cross attention (RCCA-3D) module to model the dense long-range spatiotemporal contextual information in video for action recognition.

Action Recognition Relation

Learning Defense Transformers for Counterattacking Adversarial Examples

1 code implementation13 Mar 2021 Jincheng Li, JieZhang Cao, Yifan Zhang, Jian Chen, Mingkui Tan

Relying on this, we learn a defense transformer to counterattack the adversarial examples by parameterizing the affine transformations and exploiting the boundary information of DNNs.

Adversarial Defense

StablePose: Learning 6D Object Poses from Geometrically Stable Patches

no code implementations CVPR 2021 Yifei Shi, Junwen Huang, Xin Xu, Yifan Zhang, Kai Xu

According to the theory of geometric stability analysis, a minimal set of three planar/cylindrical patches are geometrically stable and determine the full 6DoFs of the object pose.

6D Pose Estimation using RGB Object +1

Random matrix description of dynamically backscattered coherent waves propagating in a wide-field-illuminated random medium

no code implementations16 Feb 2021 Peng Miao, Yifan Zhang, Cheng Wang, Shanbao Tong

We find that the dynamic speckle patterns can be utilized to decouple the singly and multiply backscattered components.

Optics Applied Physics

Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning

1 code implementation NeurIPS 2021 Yifan Zhang, Bryan Hooi, Dapeng Hu, Jian Liang, Jiashi Feng

In this paper, we investigate whether applying contrastive learning to fine-tuning would bring further benefits, and analytically find that optimizing the contrastive loss benefits both discriminative representation learning and model optimization during fine-tuning.

Contrastive Learning Image Classification +4

Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition

1 code implementation7 Jul 2020 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

Besides, from the data aspect, we introduce a skeletal data decoupling technique to emphasize the specific characteristics of space/time and different motion scales, resulting in a more comprehensive understanding of the human actions. To test the effectiveness of the proposed method, extensive experiments are conducted on four challenging datasets for skeleton-based gesture and action recognition, namely, SHREC, DHG, NTU-60 and NTU-120, where DSTA-Net achieves state-of-the-art performance on all of them.

Action Recognition Skeleton Based Action Recognition +1

Improving Chinese Segmentation-free Word Embedding With Unsupervised Association Measure

no code implementations5 Jul 2020 Yifan Zhang, Maohua Wang, Yongjian Huang, Qianrong Gu

Recent work on segmentation-free word embedding(sembei) developed a new pipeline of word embedding for unsegmentated language while avoiding segmentation as a preprocessing step.

Segmentation valid

Relation-Aware Transformer for Portfolio Policy Learning

2 code implementations IJCAI 2020 Ke Xu, Yifan Zhang, Deheng Ye, Peilin Zhao, Mingkui Tan

One of the key issues is how to represent the non-stationary price series of assets in a portfolio, which is important for portfolio decisions.

Relation

Exemplar Loss for Siamese Network in Visual Tracking

no code implementations20 Jun 2020 Shuo Chang, Yifan Zhang, Sai Huang, Yuanyuan Yao, Zhiyong Feng

In general, Siamese tracking algorithms, supervised by logistic loss and triplet loss, increase the value of inner product between exemplar template and positive sample while reduce the value of inner product with background sample.

Visual Tracking

TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model

1 code implementation CVPR 2020 Bo Pang, Yizhuo Li, Yifan Zhang, Muchen Li, Cewu Lu

As deep learning brings excellent performances to object detection algorithms, Tracking by Detection (TBD) has become the mainstream tracking framework.

Multi-Object Tracking Object +2

Energy-Efficient Cyclical Trajectory Design for UAV-Aided Maritime Data Collection in Wind

no code implementations2 Jun 2020 Yifan Zhang, Jiangbin Lyu, Liqun Fu

We aim to minimize the UAV's energy consumption in completing the task by jointly optimizing the communication time scheduling among the buoys and the UAV's flight trajectory subject to wind effect, which is a non-convex problem and difficult to solve optimally.

Scheduling

COVID-DA: Deep Domain Adaptation from Typical Pneumonia to COVID-19

1 code implementation30 Apr 2020 Yifan Zhang, Shuaicheng Niu, Zhen Qiu, Ying WEI, Peilin Zhao, Jianhua Yao, Junzhou Huang, Qingyao Wu, Mingkui Tan

There are two main challenges: 1) the discrepancy of data distributions between domains; 2) the task difference between the diagnosis of typical pneumonia and COVID-19.

COVID-19 Diagnosis Domain Adaptation

What and Where: Modeling Skeletons from Semantic and Spatial Perspectives for Action Recognition

no code implementations7 Apr 2020 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

The two perspectives are orthogonal and complementary to each other; and by fusing them in a unified framework, our method achieves a more comprehensive understanding of the skeleton data.

Action Recognition Gesture Recognition +2

Disturbance-immune Weight Sharing for Neural Architecture Search

no code implementations29 Mar 2020 Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Yong Guo, Peilin Zhao, Junzhou Huang, Mingkui Tan

To alleviate the performance disturbance issue, we propose a new disturbance-immune update strategy for model updating.

Neural Architecture Search

Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning

no code implementations6 Mar 2020 Yifan Zhang, Peilin Zhao, Qingyao Wu, Bin Li, Junzhou Huang, Mingkui Tan

This task, however, has two main difficulties: (i) the non-stationary price series and complex asset correlations make the learning of feature representation very hard; (ii) the practicality principle in financial markets requires controlling both transaction and risk costs.

reinforcement-learning Reinforcement Learning (RL)

ForecastNet: A Time-Variant Deep Feed-Forward Neural Network Architecture for Multi-Step-Ahead Time-Series Forecasting

1 code implementation11 Feb 2020 Joel Janek Dabrowski, Yifan Zhang, Ashfaqur Rahman

Recurrent and convolutional neural networks are the most common architectures used for time series forecasting in deep learning literature.

Time Series Time Series Forecasting

Correcting for Selection Bias in Learning-to-rank Systems

no code implementations29 Jan 2020 Zohreh Ovaisi, Ragib Ahsan, Yifan Zhang, Kathryn Vasilaky, Elena Zheleva

Click data collected by modern recommendation systems are an important source of observational data that can be utilized to train learning-to-rank (LTR) systems.

counterfactual Learning-To-Rank +3

Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks

2 code implementations15 Dec 2019 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

Second, the second-order information of the skeleton data, i. e., the length and orientation of the bones, is rarely investigated, which is naturally more informative and discriminative for the human action recognition.

Action Recognition graph construction +2

Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision

no code implementations28 Nov 2019 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

Existing methods exploit the joint positions to extract the body-part features from the activation map of the convolutional networks to assist human action recognition.

Action Recognition Skeleton Based Action Recognition +1

Online Adaptive Asymmetric Active Learning with Limited Budgets

1 code implementation18 Nov 2019 Yifan Zhang, Peilin Zhao, Shuaicheng Niu, Qingyao Wu, JieZhang Cao, Junzhou Huang, Mingkui Tan

In these problems, there are two key challenges: the query budget is often limited; the ratio between classes is highly imbalanced.

Active Learning Anomaly Detection

Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis

1 code implementation17 Nov 2019 Yifan Zhang, Ying WEI, Peilin Zhao, Shuaicheng Niu, Qingyao Wu, Mingkui Tan, Junzhou Huang

In this paper, we seek to exploit rich labeled data from relevant domains to help the learning in the target task with unsupervised domain adaptation (UDA).

Unsupervised Domain Adaptation

Multi-marginal Wasserstein GAN

3 code implementations NeurIPS 2019 Jiezhang Cao, Langyuan Mo, Yifan Zhang, Kui Jia, Chunhua Shen, Mingkui Tan

Multiple marginal matching problem aims at learning mappings to match a source domain to multiple target domains and it has attracted great attention in many applications, such as multi-domain image translation.

Image Generation Translation

Non-Local Graph Convolutional Networks for Skeleton-Based Action Recognition

1 code implementation arXiv 2019 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

However, the topology of the graph is set by hand and fixed over all layers, which may be not optimal for the action recognition task and the hierarchical CNN structures.

Action Recognition Skeleton Based Action Recognition

Interpretable Complex-Valued Neural Networks for Privacy Protection

1 code implementation ICLR 2020 Liyao Xiang, Haotian Ma, Hao Zhang, Yifan Zhang, Jie Ren, Quanshi Zhang

Previous studies have found that an adversary attacker can often infer unintended input information from intermediate-layer features.

Training Binary Weight Networks via Semi-Binary Decomposition

no code implementations ECCV 2018 Qinghao Hu, Gang Li, Peisong Wang, Yifan Zhang, Jian Cheng

In this paper, we propose a novel semi-binary decomposition method which decomposes a matrix into two binary matrices and a diagonal matrix.

Computational Efficiency

Two-Step Quantization for Low-Bit Neural Networks

1 code implementation CVPR 2018 Peisong Wang, Qinghao Hu, Yifan Zhang, Chunjie Zhang, Yang Liu, Jian Cheng

In this paper, we propose a simple yet effective Two-Step Quantization (TSQ) framework, by decomposing the network quantization problem into two steps: code learning and transformation function learning based on the learned codes.

Quantization Vocal Bursts Valence Prediction

Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition

4 code implementations CVPR 2019 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing methods.

graph construction Skeleton Based Action Recognition +1

Adaptive Cost-sensitive Online Classification

no code implementations6 Apr 2018 Peilin Zhao, Yifan Zhang, Min Wu, Steven C. H. Hoi, Mingkui Tan, Junzhou Huang

Cost-Sensitive Online Classification has drawn extensive attention in recent years, where the main approach is to directly online optimize two well-known cost-sensitive metrics: (i) weighted sum of sensitivity and specificity; (ii) weighted misclassification cost.

Anomaly Detection Classification +2

Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition

no code implementations24 Apr 2017 Congqi Cao, Yifan Zhang, Chunjie Zhang, Hanqing Lu

To make it end-to-end and do not rely on any sophisticated body joint detection algorithm, we further propose a two-stream bilinear model which can learn the guidance from the body joints and capture the spatio-temporal features simultaneously.

Action Recognition Temporal Action Localization

Leveraging Multiple Domains for Sentiment Classification

no code implementations COLING 2016 Fan Yang, Arjun Mukherjee, Yifan Zhang

In addition, the learned feature representation can be used as classifier since our model defines the meaning of feature value and arranges high-level features in a prefixed order, so it is not necessary to train another classifier on top of the new features.

Classification Domain Adaptation +4

The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media Recognition

no code implementations19 Sep 2016 Ahmed Ali, Peter Bell, James Glass, Yacine Messaoui, Hamdy Mubarak, Steve Renals, Yifan Zhang

For language modelling, we made available over 110M words crawled from Aljazeera Arabic website Aljazeera. net for a 10 year duration 2000-2011.

Acoustic Modelling Language Modelling +1

Constrained Clustering and Its Application to Face Clustering in Videos

no code implementations CVPR 2013 Baoyuan Wu, Yifan Zhang, Bao-Gang Hu, Qiang Ji

As a result, many pairwise constraints between faces can be easily obtained from the temporal and spatial knowledge of the face tracks.

Constrained Clustering Face Clustering

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