Search Results for author: Mang Ye

Found 35 papers, 25 papers with code

Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark

1 code implementation12 Nov 2023 Wenke Huang, Mang Ye, Zekun Shi, Guancheng Wan, He Li, Bo Du, Qiang Yang

In this survey, we provide a systematic overview of the important and recent developments of research on federated learning.

Fairness Federated Learning +1

Rotation Invariant Transformer for Recognizing Object in UAVs

2 code implementations ACM Multimedia 2022 Shuoyi Chen, Mang Ye, Bo Du

Existing methods are usually designed for city cameras, incapable of handing the rotation issue in UAV scenarios.

Person Re-Identification Specificity

Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning

2 code implementations28 Sep 2023 Wenke Huang, Mang Ye, Zekun Shi, Bo Du

Federated learning is an important privacy-preserving multi-party learning paradigm, involving collaborative learning with others and local updating on private data.

Domain Generalization Federated Learning +1

Rethinking Client Drift in Federated Learning: A Logit Perspective

no code implementations20 Aug 2023 Yunlu Yan, Chun-Mei Feng, Mang Ye, WangMeng Zuo, Ping Li, Rick Siow Mong Goh, Lei Zhu, C. L. Philip Chen

Concretely, FedCSD introduces a class prototype similarity distillation to align the local logits with the refined global logits that are weighted by the similarity between local logits and the global prototype.

Federated Learning

An Empirical Study of CLIP for Text-based Person Search

1 code implementation19 Aug 2023 Min Cao, Yang Bai, Ziyin Zeng, Mang Ye, Min Zhang

TPBS, as a fine-grained cross-modal retrieval task, is also facing the rise of research on the CLIP-based TBPS.

Cross-Modal Retrieval Data Augmentation +4

Heterogeneous Federated Learning: State-of-the-art and Research Challenges

2 code implementations20 Jul 2023 Mang Ye, Xiuwen Fang, Bo Du, Pong C. Yuen, DaCheng Tao

Therefore, a systematic survey on this topic about the research challenges and state-of-the-art is essential.

Federated Learning

Symmetric Uncertainty-Aware Feature Transmission for Depth Super-Resolution

1 code implementation1 Jun 2023 Wuxuan Shi, Mang Ye, Bo Du

(2) For the cross-modality gap, we propose a novel Symmetric Uncertainty scheme to remove parts of RGB information harmful to the recovery of HR depth maps.


Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval

1 code implementation CVPR 2023 Ding Jiang, Mang Ye

To alleviate these issues, we present IRRA: a cross-modal Implicit Relation Reasoning and Aligning framework that learns relations between local visual-textual tokens and enhances global image-text matching without requiring additional prior supervision.

Ranked #3 on Text based Person Retrieval on RSTPReid (using extra training data)

Image-text matching Language Modelling +7

Towards Grand Unified Representation Learning for Unsupervised Visible-Infrared Person Re-Identification

1 code implementation ICCV 2023 Bin Yang, Jun Chen, Mang Ye

The grand unified representation lies in two aspects: 1) GUR adopts a bottom-up domain learning strategy with a cross-memory association embedding module to explore the information of hierarchical domains, i. e., intra-camera, inter-camera, and inter-modality domains, learning a unified and robust representation against hierarchical discrepancy.

Person Re-Identification Representation Learning

Towards Modality-Agnostic Person Re-Identification With Descriptive Query

1 code implementation CVPR 2023 Cuiqun Chen, Mang Ye, Ding Jiang

Person re-identification (ReID) with descriptive query (text or sketch) provides an important supplement for general image-image paradigms, which is usually studied in a single cross-modality matching manner, e. g., text-to-image or sketch-to-photo.

Descriptive Person Re-Identification +1

Prototype Reminiscence and Augmented Asymmetric Knowledge Aggregation for Non-Exemplar Class-Incremental Learning

no code implementations ICCV 2023 Wuxuan Shi, Mang Ye

However, since the model continuously learns new knowledge, the stored prototypical representations cannot correctly model the properties of old classes in the existence of knowledge updates.

Class Incremental Learning Incremental Learning

Unsupervised Visible-Infrared Person Re-Identification via Progressive Graph Matching and Alternate Learning

1 code implementation CVPR 2023 Zesen Wu, Mang Ye

In response, we devise a Progressive Graph Matching method to globally mine cross-modality correspondences under cluster imbalance scenarios.

Contrastive Learning Graph Matching +1

Refined Semantic Enhancement towards Frequency Diffusion for Video Captioning

1 code implementation28 Nov 2022 Xian Zhong, Zipeng Li, Shuqin Chen, Kui Jiang, Chen Chen, Mang Ye

In this paper, we introduce a novel Refined Semantic enhancement method towards Frequency Diffusion (RSFD), a captioning model that constantly perceives the linguistic representation of the infrequent tokens.

FAD Video Captioning

Augmented Dual-Contrastive Aggregation Learning for Unsupervised Visible-Infrared Person Re-Identification

1 code implementation ACM MM 2022 Bin Yang, Mang Ye, Jun Chen, Zesen Wu

Visible infrared person re-identification (VI-ReID) aims at searching out the corresponding infrared (visible) images from a gallery set captured by other spectrum cameras.

Contrastive Learning Person Re-Identification

Few-Shot Model Agnostic Federated Learning

2 code implementations Proceedings of the 30th ACM International Conference on Multimedia 2022 Wenke Huang, Mang Ye, Bo Du, Xiang Gao

To address these issues, this paper presents a novel framework with two main parts: 1) model agnostic federated learning, it performs public-private communication by unifying the model prediction outputs on the shared public datasets; 2) latent embedding adaptation, it addresses the domain gap with an adversarial learning scheme to discriminate the public and private domains.

Federated Learning

Learnable Privacy-Preserving Anonymization for Pedestrian Images

1 code implementation24 Jul 2022 Junwu Zhang, Mang Ye, Yao Yang

We further propose a progressive training strategy to improve the performance, which iteratively upgrades the initial anonymization supervision.

Person Re-Identification Privacy Preserving

Learn From Others and Be Yourself in Heterogeneous Federated Learning

1 code implementation CVPR 2022 Wenke Huang, Mang Ye, Bo Du

Federated learning has emerged as an important distributed learning paradigm, which normally involves collaborative updating with others and local updating on private data.

Continual Learning Federated Learning +2

Robust Federated Learning With Noisy and Heterogeneous Clients

4 code implementations CVPR 2022 Xiuwen Fang, Mang Ye

Model heterogeneous federated learning is a challenging task since each client independently designs its own model.

Federated Learning

AVA-AVD: Audio-Visual Speaker Diarization in the Wild

6 code implementations29 Nov 2021 Eric Zhongcong Xu, Zeyang Song, Satoshi Tsutsui, Chao Feng, Mang Ye, Mike Zheng Shou

Audio-visual speaker diarization aims at detecting "who spoke when" using both auditory and visual signals.

Relation Network speaker-diarization +1

TransHash: Transformer-based Hamming Hashing for Efficient Image Retrieval

no code implementations5 May 2021 Yongbiao Chen, Sheng Zhang, Fangxin Liu, Zhigang Chang, Mang Ye, Zhengwei Qi

Until now, the deep hashing for the image retrieval community has been dominated by convolutional neural network architectures, e. g. \texttt{Resnet}\cite{he2016deep}.

Deep Hashing Image Retrieval

Person Re-Identification by Context-aware Part Attention and Multi-Head Collaborative Learning

no code implementations IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2021 Dongming Wu, Mang Ye, Gaojie Lin, Xin Gao, Jianbing Shen

In addition, we propose a novel multi-head collaborative training scheme to improve the performance, which is collaboratively supervised by multiple heads with the same structure but different parameters.

Video-Based Person Re-Identification

Channel Augmented Joint Learning for Visible-Infrared Recognition

1 code implementation ICCV 2021 Mang Ye, Weijian Ruan, Bo Du, Mike Zheng Shou

This paper introduces a powerful channel augmented joint learning strategy for the visible-infrared recognition problem.

Data Augmentation Metric Learning

Multi-Scale Cascading Network with Compact Feature Learning for RGB-Infrared Person Re-Identification

no code implementations12 Dec 2020 Can Zhang, Hong Liu, Wei Guo, Mang Ye

RGB-Infrared person re-identification (RGB-IR Re-ID) aims to match persons from heterogeneous images captured by visible and thermal cameras, which is of great significance in the surveillance system under poor light conditions.

Person Re-Identification

Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification

5 code implementations ECCV 2020 Mang Ye, Jianbing Shen, David J. Crandall, Ling Shao, Jiebo Luo

In this paper, we propose a novel dynamic dual-attentive aggregation (DDAG) learning method by mining both intra-modality part-level and cross-modality graph-level contextual cues for VI-ReID.

Person Re-Identification Retrieval

Probabilistic Structural Latent Representation for Unsupervised Embedding

1 code implementation22 Jun 2020 Mang Ye, Jianbing Shen∗

Unsupervised embedding learning aims at extracting low-dimensional visually meaningful representations from large-scale unlabeled images, which can then be directly used for similarity-based search.

Data Augmentation

Probabilistic Structural Latent Representation for Unsupervised Embedding

no code implementations CVPR 2020 Mang Ye, Jianbing Shen

Unsupervised embedding learning aims at extracting low-dimensional visually meaningful representations from large-scale unlabeled images, which can then be directly used for similarity-based search.

Data Augmentation Image Classification

Deep Learning for Person Re-identification: A Survey and Outlook

5 code implementations13 Jan 2020 Mang Ye, Jianbing Shen, Gaojie Lin, Tao Xiang, Ling Shao, Steven C. H. Hoi

The widely studied closed-world setting is usually applied under various research-oriented assumptions, and has achieved inspiring success using deep learning techniques on a number of datasets.

Cross-Modal Person Re-Identification Metric Learning +2

Unsupervised Embedding Learning via Invariant and Spreading Instance Feature

1 code implementation CVPR 2019 Mang Ye, Xu Zhang, Pong C. Yuen, Shih-Fu Chang

This paper studies the unsupervised embedding learning problem, which requires an effective similarity measurement between samples in low-dimensional embedding space.

Data Augmentation

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