Search Results for author: Feng Zhu

Found 67 papers, 21 papers with code

When Demands Evolve Larger and Noisier: Learning and Earning in a Growing Environment

no code implementations ICML 2020 Feng Zhu, Zeyu Zheng

Finally, we consider an analogous non-stationary setting in the canonical multi-armed bandit problem, and points out that the \textit{any-time} situation and the \textit{fixed-time} situation render the same optimal regret order in a simple form, in contrast to the dynamic pricing problem.

DRAG: Divergence-based Adaptive Aggregation in Federated learning on Non-IID Data

no code implementations4 Sep 2023 Feng Zhu, Jingjing Zhang, Shengyun Liu, Xin Wang

Local stochastic gradient descent (SGD) is a fundamental approach in achieving communication efficiency in Federated Learning (FL) by allowing individual workers to perform local updates.

Federated Learning

Freshness or Accuracy, Why Not Both? Addressing Delayed Feedback via Dynamic Graph Neural Networks

no code implementations15 Aug 2023 Xiaolin Zheng, Zhongyu Wang, Chaochao Chen, Feng Zhu, Jiashu Qian

In the model training, we propose a novel graph convolutional method named HLGCN, which leverages both high-pass and low-pass filters to deal with conversion and non-conversion relationships.

Link-Context Learning for Multimodal LLMs

1 code implementation15 Aug 2023 Yan Tai, Weichen Fan, Zhao Zhang, Feng Zhu, Rui Zhao, Ziwei Liu

The ability to learn from context with novel concepts, and deliver appropriate responses are essential in human conversations.

Few-Shot Learning Novel Concepts

Relation-Aware Distribution Representation Network for Person Clustering with Multiple Modalities

no code implementations1 Aug 2023 Kaijian Liu, Shixiang Tang, Ziyue Li, Zhishuai Li, Lei Bai, Feng Zhu, Rui Zhao

The distribution representation of a clue is a vector consisting of the relation between this clue and all other clues from all modalities, thus being modality agnostic and good for person clustering.

Clustering

Domain Disentanglement with Interpolative Data Augmentation for Dual-Target Cross-Domain Recommendation

no code implementations26 Jul 2023 JiaJie Zhu, Yan Wang, Feng Zhu, Zhu Sun

In DIDA-CDR, we first propose an interpolative data augmentation approach to generating both relevant and diverse augmented user representations to augment sparser domain and explore potential user preferences.

Data Augmentation Disentanglement

Exposing the Troublemakers in Described Object Detection

1 code implementation24 Jul 2023 Chi Xie, Zhao Zhang, Yixuan Wu, Feng Zhu, Rui Zhao, Shuang Liang

In this paper, we advance them to a more practical setting called Described Object Detection (DOD) by expanding category names to flexible language expressions for OVD and overcoming the limitation of REC to only grounding the pre-existing object.

Binary Classification object-detection +3

Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning

no code implementations23 Jun 2023 Shaofeng Zhang, Feng Zhu, Rui Zhao, Junchi Yan

On classification tasks, for ViT-S, ADCLR achieves 77. 5% top-1 accuracy on ImageNet with linear probing, outperforming our baseline (DINO) without our devised techniques as plug-in, by 0. 5%.

Instance Segmentation object-detection +4

Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis

1 code implementation15 Jun 2023 Xiaoshi Wu, Yiming Hao, Keqiang Sun, Yixiong Chen, Feng Zhu, Rui Zhao, Hongsheng Li

By fine-tuning CLIP on HPD v2, we obtain Human Preference Score v2 (HPS v2), a scoring model that can more accurately predict human preferences on generated images.

Image Generation

Retrieve Anyone: A General-purpose Person Re-identification Task with Instructions

no code implementations13 Jun 2023 Weizhen He, Shixiang Tang, Yiheng Deng, Qihao Chen, Qingsong Xie, Yizhou Wang, Lei Bai, Feng Zhu, Rui Zhao, Wanli Ouyang, Donglian Qi, Yunfeng Yan

This paper strives to resolve this problem by proposing a new instruct-ReID task that requires the model to retrieve images according to the given image or language instructions. Our instruct-ReID is a more general ReID setting, where existing ReID tasks can be viewed as special cases by designing different instructions.

Person Re-Identification

Advancing Referring Expression Segmentation Beyond Single Image

1 code implementation ICCV 2023 Yixuan Wu, Zhao Zhang, Xie Chi, Feng Zhu, Rui Zhao

To overcome this limitation, we propose a more realistic and general setting, named Group-wise Referring Expression Segmentation (GRES), which expands RES to a collection of related images, allowing the described objects to be present in a subset of input images.

Co-Salient Object Detection object-detection +3

Regret Distribution in Stochastic Bandits: Optimal Trade-off between Expectation and Tail Risk

no code implementations10 Apr 2023 David Simchi-Levi, Zeyu Zheng, Feng Zhu

A novel policy is proposed to characterize the optimal regret tail probability for any regret threshold.

Human Preference Score: Better Aligning Text-to-Image Models with Human Preference

2 code implementations ICCV 2023 Xiaoshi Wu, Keqiang Sun, Feng Zhu, Rui Zhao, Hongsheng Li

To address this issue, we collect a dataset of human choices on generated images from the Stable Foundation Discord channel.

CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching

1 code implementation CVPR 2023 Xiaoshi Wu, Feng Zhu, Rui Zhao, Hongsheng Li

To overcome these obstacles, we propose CORA, a DETR-style framework that adapts CLIP for Open-vocabulary detection by Region prompting and Anchor pre-matching.

Ranked #2 on Open Vocabulary Object Detection on MSCOCO (using extra training data)

object-detection Object Localization +1

HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining

1 code implementation CVPR 2023 Shixiang Tang, Cheng Chen, Qingsong Xie, Meilin Chen, Yizhou Wang, Yuanzheng Ci, Lei Bai, Feng Zhu, Haiyang Yang, Li Yi, Rui Zhao, Wanli Ouyang

Specifically, we propose a \textbf{HumanBench} based on existing datasets to comprehensively evaluate on the common ground the generalization abilities of different pretraining methods on 19 datasets from 6 diverse downstream tasks, including person ReID, pose estimation, human parsing, pedestrian attribute recognition, pedestrian detection, and crowd counting.

Autonomous Driving Crowd Counting +4

UniHCP: A Unified Model for Human-Centric Perceptions

1 code implementation CVPR 2023 Yuanzheng Ci, Yizhou Wang, Meilin Chen, Shixiang Tang, Lei Bai, Feng Zhu, Rui Zhao, Fengwei Yu, Donglian Qi, Wanli Ouyang

When adapted to a specific task, UniHCP achieves new SOTAs on a wide range of human-centric tasks, e. g., 69. 8 mIoU on CIHP for human parsing, 86. 18 mA on PA-100K for attribute prediction, 90. 3 mAP on Market1501 for ReID, and 85. 8 JI on CrowdHuman for pedestrian detection, performing better than specialized models tailored for each task.

2D Pose Estimation Human Parsing +7

Saliency Guided Contrastive Learning on Scene Images

no code implementations22 Feb 2023 Meilin Chen, Yizhou Wang, Shixiang Tang, Feng Zhu, Haiyang Yang, Lei Bai, Rui Zhao, Donglian Qi, Wanli Ouyang

Despite being feasible, recent works largely overlooked discovering the most discriminative regions for contrastive learning to object representations in scene images.

Contrastive Learning Representation Learning +1

DCMT: A Direct Entire-Space Causal Multi-Task Framework for Post-Click Conversion Estimation

no code implementations13 Feb 2023 Feng Zhu, Mingjie Zhong, Xinxing Yang, Longfei Li, Lu Yu, Tiehua Zhang, Jun Zhou, Chaochao Chen, Fei Wu, Guanfeng Liu, Yan Wang

In recommendation scenarios, there are two long-standing challenges, i. e., selection bias and data sparsity, which lead to a significant drop in prediction accuracy for both Click-Through Rate (CTR) and post-click Conversion Rate (CVR) tasks.

Multi-Task Learning Selection bias

CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision

no code implementations ICCV 2023 Yuguang Li, Kai Wang, Hui Li, Seon-Min Rhee, Seungju Han, JiHye Kim, Min Yang, Ran Yang, Feng Zhu

Meanwhile, SANE easily establishes multi-task learning with CORE loss functions on both depth and surface normal estimation, leading to the whole performance leap.

Depth Estimation Multi-Task Learning +2

Simulating single-photon detector array sensors for depth imaging

1 code implementation7 Oct 2022 Stirling Scholes, Germán Mora-Martín, Feng Zhu, Istvan Gyongy, Phil Soan, Jonathan Leach

Our approach accurately generates realistic depth images in a wide range of scenarios, allowing the performance of an optical depth imaging system to be established without the need for costly and laborious field testing.

object-detection Object Detection +1

STSyn: Speeding Up Local SGD with Straggler-Tolerant Synchronization

no code implementations6 Oct 2022 Feng Zhu, Jingjing Zhang, Xin Wang

Synchronous local stochastic gradient descent (local SGD) suffers from some workers being idle and random delays due to slow and straggling workers, as it waits for the workers to complete the same amount of local updates.

BoW3D: Bag of Words for Real-Time Loop Closing in 3D LiDAR SLAM

1 code implementation15 Aug 2022 Yunge Cui, Xieyuanli Chen, Yinlong Zhang, Jiahua Dong, Qingxiao Wu, Feng Zhu

To address this limitation, we present a novel Bag of Words for real-time loop closing in 3D LiDAR SLAM, called BoW3D.

Simultaneous Localization and Mapping

Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation

1 code implementation5 Aug 2022 Feng Zhu, Zongxin Yang, Xin Yu, Yi Yang, Yunchao Wei

In this work, we propose a new online VIS paradigm named Instance As Identity (IAI), which models temporal information for both detection and tracking in an efficient way.

Instance Segmentation Semantic Segmentation +1

Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification

no code implementations1 Aug 2022 Xulin Li, Yan Lu, Bin Liu, Yating Liu, Guojun Yin, Qi Chu, Jinyang Huang, Feng Zhu, Rui Zhao, Nenghai Yu

But we find existing graph-based methods in the visible-infrared person re-identification task (VI-ReID) suffer from bad generalization because of two issues: 1) train-test modality balance gap, which is a property of VI-ReID task.

Person Re-Identification

COOR-PLT: A hierarchical control model for coordinating adaptive platoons of connected and autonomous vehicles at signal-free intersections based on deep reinforcement learning

no code implementations1 Jul 2022 Duowei Li, Jianping Wu, Feng Zhu, Tianyi Chen, Yiik Diew Wong

The simulation results demonstrate that the model is able to: (1) achieve satisfactory convergence performances; (2) adaptively determine platoon size in response to varying traffic conditions; and (3) completely avoid deadlocks at the intersection.

Autonomous Vehicles Fairness

Modeling Adaptive Platoon and Reservation Based Autonomous Intersection Control: A Deep Reinforcement Learning Approach

no code implementations24 Jun 2022 Duowei Li, Jianping Wu, Feng Zhu, Tianyi Chen, Yiik Diew Wong

As a strategy to reduce travel delay and enhance energy efficiency, platooning of connected and autonomous vehicles (CAVs) at non-signalized intersections has become increasingly popular in academia.

Autonomous Vehicles Reinforcement Learning (RL)

LinK3D: Linear Keypoints Representation for 3D LiDAR Point Cloud

1 code implementation13 Jun 2022 Yunge Cui, Yinlong Zhang, Jiahua Dong, Haibo Sun, Feng Zhu

In this paper, we has applied our LinK3D to 3D registration, LiDAR odometry and place recognition tasks, and achieved competitive results compared with the state-of-the-art methods.

3D Object Detection object-detection

A Simple and Optimal Policy Design with Safety against Heavy-tailed Risk for Stochastic Bandits

no code implementations7 Jun 2022 David Simchi-Levi, Zeyu Zheng, Feng Zhu

Starting from the two-armed bandit setting with time horizon $T$, we propose a simple policy and prove that the policy (i) enjoys the worst-case optimality for the expected regret at order $O(\sqrt{T\ln T})$ and (ii) has the worst-case tail probability of incurring a linear regret decay at an exponential rate $\exp(-\Omega(\sqrt{T}))$, a rate that we prove to be best achievable for all worst-case optimal policies.

Multi-Armed Bandits Thompson Sampling

Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domains

no code implementations10 May 2022 Haiyang Yang, Meilin Chen, Yizhou Wang, Shixiang Tang, Feng Zhu, Lei Bai, Rui Zhao, Wanli Ouyang

While recent self-supervised learning methods have achieved good performances with evaluation set on the same domain as the training set, they will have an undesirable performance decrease when tested on a different domain.

Self-Supervised Learning

Time Dependency, Data Flow, and Competitive Advantage

no code implementations17 Mar 2022 Ehsan Valavi, Joel Hestness, Marco Iansiti, Newsha Ardalani, Feng Zhu, Karim R. Lakhani

Relating the text topics to various business areas of interest, we argue that competing in a business area in which data value decays rapidly alters strategies to acquire competitive advantage.

Adaptive Worker Grouping For Communication-Efficient and Straggler-Tolerant Distributed SGD

no code implementations12 Jan 2022 Feng Zhu, Jingjing Zhang, Osvaldo Simeone, Xin Wang

Wall-clock convergence time and communication load are key performance metrics for the distributed implementation of stochastic gradient descent (SGD) in parameter server settings.

Learning Memory-Augmented Unidirectional Metrics for Cross-Modality Person Re-Identification

no code implementations CVPR 2022 Jialun Liu, Yifan Sun, Feng Zhu, Hongbin Pei, Yi Yang, Wenhui Li

These two unidirectional metrics (IR image to RGB proxy and RGB image to IR proxy) jointly alleviate the relay effect and benefit cross-modality association.

Cross-Modality Person Re-identification Person Re-Identification

GPS: A Policy-driven Sampling Approach for Graph Representation Learning

no code implementations29 Dec 2021 Tiehua Zhang, Yuze Liu, Xin Chen, Xiaowei Huang, Feng Zhu, Xi Zheng

Graph representation learning has drawn increasing attention in recent years, especially for learning the low dimensional embedding at both node and graph level for classification and recommendations tasks.

Graph Classification Graph Representation Learning

Feature Erasing and Diffusion Network for Occluded Person Re-Identification

1 code implementation CVPR 2022 Zhikang Wang, Feng Zhu, Shixiang Tang, Rui Zhao, Lihuo He, Jiangning Song

With the guidance of the occlusion scores from OEM, the feature diffusion process is mainly conducted on visible body parts, which guarantees the quality of the synthesized NTP characteristics.

 Ranked #1 on Person Re-Identification on Occluded REID (Rank-1 metric)

Person Re-Identification

DronePose: The identification, segmentation, and orientation detection of drones via neural networks

no code implementations10 Dec 2021 Stirling Scholes, Alice Ruget, German Mora-Martin, Feng Zhu, Istvan Gyongy, Jonathan Leach

The growing ubiquity of drones has raised concerns over the ability of traditional air-space monitoring technologies to accurately characterise such vehicles.

Real-time, low-cost multi-person 3D pose estimation

no code implementations11 Oct 2021 Alice Ruget, Max Tyler, Germán Mora Martín, Stirling Scholes, Feng Zhu, Istvan Gyongy, Brent Hearn, Steve McLaughlin, Abderrahim Halimi, Jonathan Leach

The process of tracking human anatomy in computer vision is referred to pose estimation, and it is used in fields ranging from gaming to surveillance.

3D Multi-Person Pose Estimation 3D Pose Estimation +4

Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learning

no code implementations ICLR 2022 Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, Xiaokang Yang

The proposed two methods (FCL, ICL) can be combined synthetically, called Zero-CL, where ``Zero'' means negative samples are \textbf{zero} relevant, which allows Zero-CL to completely discard negative pairs i. e., with \textbf{zero} negative samples.

Contrastive Learning

Temporal RoI Align for Video Object Recognition

1 code implementation8 Sep 2021 Tao Gong, Kai Chen, Xinjiang Wang, Qi Chu, Feng Zhu, Dahua Lin, Nenghai Yu, Huamin Feng

In this work, considering the features of the same object instance are highly similar among frames in a video, a novel Temporal RoI Align operator is proposed to extract features from other frames feature maps for current frame proposals by utilizing feature similarity.

Instance Segmentation object-detection +4

A Unified Framework for Cross-Domain and Cross-System Recommendations

no code implementations18 Aug 2021 Feng Zhu, Yan Wang, Jun Zhou, Chaochao Chen, Longfei Li, Guanfeng Liu

Moreover, to avoid negative transfer, we further propose a Personalized training strategy to minimize the embedding difference of common entities between a richer dataset and a sparser dataset, deriving three new models, i. e., GA-DTCDR-P, GA-MTCDR-P, and GA-CDR+CSR-P, for the three scenarios respectively.

Graph Embedding

A new method for vehicle system safety design based on data mining with uncertainty modeling

no code implementations12 Jul 2021 Xianping Du, Binhui Jiang, Feng Zhu

In this research, a new data mining-based design approach has been developed for designing complex mechanical systems such as a crashworthy passenger car with uncertainty modeling.

Offline Planning and Online Learning under Recovering Rewards

no code implementations28 Jun 2021 David Simchi-Levi, Zeyu Zheng, Feng Zhu

Motivated by emerging applications such as live-streaming e-commerce, promotions and recommendations, we introduce and solve a general class of non-stationary multi-armed bandit problems that have the following two features: (i) the decision maker can pull and collect rewards from up to $K\,(\ge 1)$ out of $N$ different arms in each time period; (ii) the expected reward of an arm immediately drops after it is pulled, and then non-parametrically recovers as the arm's idle time increases.

Improving Facial Attribute Recognition by Group and Graph Learning

no code implementations28 May 2021 Zhenghao Chen, Shuhang Gu, Feng Zhu, Jing Xu, Rui Zhao

For the spatial correlation, we aggregate attributes with spatial similarity into a part-based group and then introduce a Group Attention Learning to generate the group attention and the part-based group feature.

Graph Learning

Minimization of ion micromotion with artificial neural network

no code implementations3 Mar 2021 Yang Liu, Qi-feng Lao, Peng-fei Lu, Xin-xin Rao, Hao Wu, Teng Liu, Kun-xu Wang, Zhao Wang, Ming-shen Li, Feng Zhu, Luo Le

Minimizing the micromotion of the single trapped ion in a linear Paul trap is a tedious and time-consuming work, but is of great importance in cooling the ion into the motional ground state as well as maintaining long coherence time, which is crucial for quantum information processing and quantum computation.

Atomic Physics Quantum Physics

Cross-Domain Recommendation: Challenges, Progress, and Prospects

no code implementations2 Mar 2021 Feng Zhu, Yan Wang, Chaochao Chen, Jun Zhou, Longfei Li, Guanfeng Liu

To address the long-standing data sparsity problem in recommender systems (RSs), cross-domain recommendation (CDR) has been proposed to leverage the relatively richer information from a richer domain to improve the recommendation performance in a sparser domain.

Recommendation Systems

Progressive Correspondence Pruning by Consensus Learning

no code implementations ICCV 2021 Chen Zhao, Yixiao Ge, Feng Zhu, Rui Zhao, Hongsheng Li, Mathieu Salzmann

Correspondence selection aims to correctly select the consistent matches (inliers) from an initial set of putative correspondences.

Denoising Pose Estimation +1

A Deep Framework for Cross-Domain and Cross-System Recommendations

no code implementations14 Sep 2020 Feng Zhu, Yan Wang, Chaochao Chen, Guanfeng Liu, Mehmet Orgun, Jia Wu

Therefore, finding an accurate mapping of the latent factors across domains or systems is crucial to enhancing recommendation accuracy.

Recommendation Systems

Self-supervising Fine-grained Region Similarities for Large-scale Image Localization

3 code implementations ECCV 2020 Yixiao Ge, Haibo Wang, Feng Zhu, Rui Zhao, Hongsheng Li

The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset.

Image Retrieval Retrieval

Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID

4 code implementations14 Mar 2020 Yixiao Ge, Feng Zhu, Dapeng Chen, Rui Zhao, Xiaogang Wang, Hongsheng Li

To tackle the challenges, we propose an end-to-end structured domain adaptation framework with an online relation-consistency regularization term.

Pseudo Label Translation +2

Towards Unified INT8 Training for Convolutional Neural Network

no code implementations CVPR 2020 Feng Zhu, Ruihao Gong, Fengwei Yu, Xianglong Liu, Yanfei Wang, Zhelong Li, Xiuqi Yang, Junjie Yan

In this paper, we give an attempt to build a unified 8-bit (INT8) training framework for common convolutional neural networks from the aspects of both accuracy and speed.

object-detection Object Detection +1

Clustering Bioactive Molecules in 3D Chemical Space with Unsupervised Deep Learning

no code implementations9 Feb 2019 Chu Qin, Ying Tan, Shang Ying Chen, Xian Zeng, Xingxing Qi, Tian Jin, Huan Shi, Yiwei Wan, Yu Chen, Jingfeng Li, Weidong He, Yali Wang, Peng Zhang, Feng Zhu, Hongping Zhao, Yuyang Jiang, Yuzong Chen

We ex-plored the superior learning capability of deep autoencoders for unsupervised clustering of 1. 39 mil-lion bioactive molecules into band-clusters in a 3-dimensional latent chemical space.

Clustering Drug Discovery

Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification

2 code implementations CVPR 2017 Feng Zhu, Hongsheng Li, Wanli Ouyang, Nenghai Yu, Xiaogang Wang

Analysis of the learned SRN model demonstrates that it can effectively capture both semantic and spatial relations of labels for improving classification performance.

Classification General Classification +2

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