Search Results for author: Shiming Ge

Found 47 papers, 15 papers with code

COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking

1 code implementation2 Apr 2025 Chunhui Zhang, Li Liu, Jialin Gao, Xin Sun, Hao Wen, Xi Zhou, Shiming Ge, Yanfeng Wang

In this work, we propose COST, a contrastive one-stage transformer fusion framework for VL tracking, aiming to learn semantically consistent and unified VL representations.

cross-modal alignment Object +1

Towards Personalized Federated Learning via Comprehensive Knowledge Distillation

no code implementations6 Nov 2024 Pengju Wang, Bochao Liu, Weijia Guo, Yong Li, Shiming Ge

By applying knowledge distillation, we effectively transfer global generalized knowledge and historical personalized knowledge to the local model, thus mitigating catastrophic forgetting and enhancing the general performance of personalized models.

Knowledge Distillation Personalized Federated Learning

Personalized Federated Learning via Backbone Self-Distillation

no code implementations24 Sep 2024 Pengju Wang, Bochao Liu, Dan Zeng, Chenggang Yan, Shiming Ge

These weights are then aggregated to create a global backbone, which is returned to each client for updating.

Personalized Federated Learning Transfer Learning

Federated Learning with Label-Masking Distillation

1 code implementation20 Sep 2024 Jianghu Lu, Shikun Li, Kexin Bao, Pengju Wang, Zhenxing Qian, Shiming Ge

Inspired by this, we propose a label-masking distillation approach termed FedLMD to facilitate federated learning via perceiving the various label distributions of each client.

Federated Learning Privacy Preserving

Interpret the Predictions of Deep Networks via Re-Label Distillation

no code implementations20 Sep 2024 Yingying Hua, Shiming Ge, Daichi Zhang

After that, using the labels annotated by the deep network as teacher, a linear student model is trained to approximate the annotations by mapping these synthetic images to the classes.

Look Through Masks: Towards Masked Face Recognition with De-Occlusion Distillation

no code implementations19 Sep 2024 Chenyu Li, Shiming Ge, Daichi Zhang, Jia Li

Many real-world applications today like video surveillance and urban governance need to address the recognition of masked faces, where content replacement by diverse masks often brings in incomplete appearance and ambiguous representation, leading to a sharp drop in accuracy.

Face Recognition Facial Inpainting +1

Distilling Channels for Efficient Deep Tracking

no code implementations18 Sep 2024 Shiming Ge, Zhao Luo, Chunhui Zhang, Yingying Hua, DaCheng Tao

However, these networks are too complex to represent a specific moving object, leading to poor generalization as well as high computational and memory costs.

Feature Compression Visual Tracking

Efficient Low-Resolution Face Recognition via Bridge Distillation

no code implementations18 Sep 2024 Shiming Ge, Shengwei Zhao, Chenyu Li, Yu Zhang, Jia Li

Face recognition in the wild is now advancing towards light-weight models, fast inference speed and resolution-adapted capability.

Dataset Distillation Face Model +2

Distilling Generative-Discriminative Representations for Very Low-Resolution Face Recognition

no code implementations10 Sep 2024 Junzheng Zhang, Weijia Guo, Bochao Liu, Ruixin Shi, Yong Li, Shiming Ge

After that, the discriminative representation distillation further considers a pretrained face recognizer as the discriminative teacher to supervise the learning of the student head via cross-resolution relational contrastive distillation.

Face Recognition Knowledge Distillation +2

Look One and More: Distilling Hybrid Order Relational Knowledge for Cross-Resolution Image Recognition

no code implementations9 Sep 2024 Shiming Ge, Kangkai Zhang, Haolin Liu, Yingying Hua, Shengwei Zhao, Xin Jin, Hao Wen

In spite of great success in many image recognition tasks achieved by recent deep models, directly applying them to recognize low-resolution images may suffer from low accuracy due to the missing of informative details during resolution degradation.

Face Recognition Image Classification +3

Low-Resolution Object Recognition with Cross-Resolution Relational Contrastive Distillation

no code implementations4 Sep 2024 Kangkai Zhang, Shiming Ge, Ruixin Shi, Dan Zeng

Recent studies have shown that knowledge distillation approaches can effectively transfer knowledge from a high-resolution teacher model to a low-resolution student model by aligning cross-resolution representations.

Face Recognition Knowledge Distillation +2

Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation

no code implementations4 Sep 2024 Shiming Ge, Bochao Liu, Pengju Wang, Yong Li, Dan Zeng

In this work, we propose a discriminative-generative distillation approach to learn privacy-preserving deep models.

Privacy Preserving Transfer Learning

Low-Resolution Face Recognition via Adaptable Instance-Relation Distillation

no code implementations3 Sep 2024 Ruixin Shi, Weijia Guo, Shiming Ge

In this manner, the capability of recovering missing details of familiar low-resolution faces can be effectively enhanced, leading to a better knowledge transfer.

Face Recognition Knowledge Distillation +2

Learning Differentially Private Diffusion Models via Stochastic Adversarial Distillation

no code implementations27 Aug 2024 Bochao Liu, Pengju Wang, Shiming Ge

Specifically, we first train a diffusion model as a teacher and then train a student by distillation, in which we achieve differential privacy by adding noise to the gradients from other models to the student.

Learning Natural Consistency Representation for Face Forgery Video Detection

no code implementations15 Jul 2024 Daichi Zhang, Zihao Xiao, Shikun Li, Fanzhao Lin, Jianmin Li, Shiming Ge

To this end, we propose to learn the Natural Consistency representation (NACO) of real face videos in a self-supervised manner, which is inspired by the observation that fake videos struggle to maintain the natural spatiotemporal consistency even under unknown forgery methods and different perturbations.

Representation Learning Video Classification

DANCE: Dual-View Distribution Alignment for Dataset Condensation

1 code implementation3 Jun 2024 Hansong Zhang, Shikun Li, Fanzhao Lin, Weiping Wang, Zhenxing Qian, Shiming Ge

Specifically, from the inner-class view, we construct multiple "middle encoders" to perform pseudo long-term distribution alignment, making the condensed set a good proxy of the real one during the whole training process; while from the inter-class view, we use the expert models to perform distribution calibration, ensuring the synthetic data remains in the real class region during condensing.

Dataset Condensation

Masked Face Recognition with Generative-to-Discriminative Representations

no code implementations27 May 2024 Shiming Ge, Weijia Guo, Chenyu Li, Junzheng Zhang, Yong Li, Dan Zeng

First, we leverage a generative encoder pretrained for face inpainting and finetune it to represent masked faces into category-aware descriptors.

Attribute Face Recognition +1

M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy

2 code implementations26 Dec 2023 Hansong Zhang, Shikun Li, Pengju Wang, Dan Zeng, Shiming Ge

Nowadays, optimization-oriented methods have been the primary method in the field of dataset condensation for achieving SOTA results.

Dataset Condensation

Coupled Confusion Correction: Learning from Crowds with Sparse Annotations

2 code implementations12 Dec 2023 Hansong Zhang, Shikun Li, Dan Zeng, Chenggang Yan, Shiming Ge

Moreover, we cluster the ``annotator groups'' who share similar expertise so that their confusion matrices could be corrected together.

Multi-Label Noise Transition Matrix Estimation with Label Correlations: Theory and Algorithm

1 code implementation22 Sep 2023 Shikun Li, Xiaobo Xia, Hansong Zhang, Shiming Ge, Tongliang Liu

However, estimating multi-label noise transition matrices remains a challenging task, as most existing estimators in noisy multi-class learning rely on anchor points and accurate fitting of noisy class posteriors, which is hard to satisfy in noisy multi-label learning.

Multi-Label Learning

Latent Spatiotemporal Adaptation for Generalized Face Forgery Video Detection

no code implementations9 Sep 2023 Daichi Zhang, Zihao Xiao, Jianmin Li, Shiming Ge

Specifically, we first model the spatiotemporal patterns of face videos by incorporating a lightweight CNN to extract local spatial features of each frame and then cascading a vision transformer to learn the long-term spatiotemporal representations in latent space, which should contain more clues than in pixel space.

Contrastive Learning Representation Learning

Transferring Annotator- and Instance-dependent Transition Matrix for Learning from Crowds

1 code implementation5 Jun 2023 Shikun Li, Xiaobo Xia, Jiankang Deng, Shiming Ge, Tongliang Liu

In real-world crowd-sourcing scenarios, noise transition matrices are both annotator- and instance-dependent.

Transfer Learning

Private Gradient Estimation is Useful for Generative Modeling

no code implementations18 May 2023 Bochao Liu, Pengju Wang, Weijia Guo, Yong Li, Liansheng Zhuang, Weiping Wang, Shiming Ge

In this work, we present a new private generative modeling approach where samples are generated via Hamiltonian dynamics with gradients of the private dataset estimated by a well-trained network.

Image Generation Privacy Preserving

Deepfake Video Detection with Spatiotemporal Dropout Transformer

no code implementations14 Jul 2022 Daichi Zhang, Fanzhao Lin, Yingying Hua, Pengju Wang, Dan Zeng, Shiming Ge

Existing image-level approaches often focus on single frame and ignore the spatiotemporal cues hidden in deepfake videos, resulting in poor generalization and robustness.

Data Augmentation Face Swapping

Bootstrapping Multi-view Representations for Fake News Detection

1 code implementation12 Jun 2022 Qichao Ying, Xiaoxiao Hu, Yangming Zhou, Zhenxing Qian, Dan Zeng, Shiming Ge

Representations from each view are separately used to coarsely predict the fidelity of the whole news, and the multimodal representations are able to predict the cross-modal consistency.

Decision Making Fake News Detection

Robust Weight Perturbation for Adversarial Training

1 code implementation30 May 2022 Chaojian Yu, Bo Han, Mingming Gong, Li Shen, Shiming Ge, Bo Du, Tongliang Liu

Based on these observations, we propose a robust perturbation strategy to constrain the extent of weight perturbation.

Classification

Trustable Co-label Learning from Multiple Noisy Annotators

1 code implementation8 Mar 2022 Shikun Li, Tongliang Liu, Jiyong Tan, Dan Zeng, Shiming Ge

This raises the following important question: how can we effectively use a small amount of trusted data to facilitate robust classifier learning from multiple annotators?

Selective-Supervised Contrastive Learning with Noisy Labels

1 code implementation CVPR 2022 Shikun Li, Xiaobo Xia, Shiming Ge, Tongliang Liu

In the selection process, by measuring the agreement between learned representations and given labels, we first identify confident examples that are exploited to build confident pairs.

Contrastive Learning Learning with noisy labels +1

WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking

1 code implementation19 Jan 2022 Chunhui Zhang, Guanjie Huang, Li Liu, Shan Huang, Yinan Yang, Xiang Wan, Shiming Ge, DaCheng Tao

In this work, we propose WebUAV-3M, the largest public UAV tracking benchmark to date, to facilitate both the development and evaluation of deep UAV trackers.

The 2nd Anti-UAV Workshop & Challenge: Methods and Results

no code implementations23 Aug 2021 Jian Zhao, Gang Wang, Jianan Li, Lei Jin, Nana Fan, Min Wang, Xiaojuan Wang, Ting Yong, Yafeng Deng, Yandong Guo, Shiming Ge, Guodong Guo

The 2nd Anti-UAV Workshop \& Challenge aims to encourage research in developing novel and accurate methods for multi-scale object tracking.

Object Tracking

Interpretable Face Manipulation Detection via Feature Whitening

no code implementations21 Jun 2021 Yingying Hua, Daichi Zhang, Pengju Wang, Shiming Ge

The approach could make the face manipulation detection process transparent by embedding the feature whitening module.

Fairness

Student Network Learning via Evolutionary Knowledge Distillation

no code implementations23 Mar 2021 Kangkai Zhang, Chunhui Zhang, Shikun Li, Dan Zeng, Shiming Ge

Inspired by that, we propose an evolutionary knowledge distillation approach to improve the transfer effectiveness of teacher knowledge.

Knowledge Distillation Transfer Learning

Receptive Multi-granularity Representation for Person Re-Identification

no code implementations31 Aug 2020 Guanshuo Wang, Yufeng Yuan, Jiwei Li, Shiming Ge, Xi Zhou

Current stripe-based feature learning approaches have delivered impressive accuracy, but do not make a proper trade-off between diversity, locality, and robustness, which easily suffers from part semantic inconsistency for the conflict between rigid partition and misalignment.

Person Re-Identification

Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition

no code implementations24 Dec 2019 Jialin Gao, Tong He, Xi Zhou, Shiming Ge

A collection of approaches based on graph convolutional networks have proven success in skeleton-based action recognition by exploring neighborhood information and dense dependencies between intra-frame joints.

Action Recognition Skeleton Based Action Recognition

Aesthetic Attributes Assessment of Images

2 code implementations11 Jul 2019 Xin Jin, Le Wu, Geng Zhao, Xiao-Dong Li, Xiaokun Zhang, Shiming Ge, Dongqing Zou, Bin Zhou, Xinghui Zhou

This is a new formula of image aesthetic assessment, which predicts aesthetic attributes captions together with the aesthetic score of each attribute.

Attribute Image Captioning +1

Domain Adaptive Attention Learning for Unsupervised Person Re-Identification

no code implementations25 May 2019 Yangru Huang, Peixi Peng, Yi Jin, Yidong Li, Junliang Xing, Shiming Ge

In this approach, a domain adaptive attention model is learned to separate the feature map into domain-shared part and domain-specific part.

Diversity Domain Adaptation +3

Spatiotemporal Knowledge Distillation for Efficient Estimation of Aerial Video Saliency

no code implementations10 Apr 2019 Jia Li, Kui Fu, Shengwei Zhao, Shiming Ge

In this approach, five components are involved, including two teachers, two students and the desired spatiotemporal model.

Knowledge Distillation Saliency Prediction

Ultrafast Video Attention Prediction with Coupled Knowledge Distillation

no code implementations9 Apr 2019 Kui Fu, Peipei Shi, Yafei Song, Shiming Ge, Xiangju Lu, Jia Li

To address these issues, we design an extremely light-weight network with ultrafast speed, named UVA-Net.

Knowledge Distillation Prediction

Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation

no code implementations25 Nov 2018 Shiming Ge, Shengwei Zhao, Chenyu Li, Jia Li

In this approach, a two-stream convolutional neural network (CNN) is first initialized to recognize high-resolution faces and resolution-degraded faces with a teacher stream and a student stream, respectively.

Face Model Face Recognition +1

Single Reference Image based Scene Relighting via Material Guided Filtering

no code implementations23 Aug 2017 Xin Jin, Yannan Li, Ningning Liu, Xiao-Dong Li, Xianggang Jiang, Chaoen Xiao, Shiming Ge

We propose a novel outdoor scene relighting method, which needs only a single reference image and is based on material constrained layer decomposition.

Image Relighting

Predicting Aesthetic Score Distribution through Cumulative Jensen-Shannon Divergence

2 code implementations23 Aug 2017 Xin Jin, Le Wu, Xiao-Dong Li, Siyu Chen, Siwei Peng, Jingying Chi, Shiming Ge, Chenggen Song, Geng Zhao

Thus, a novel CNN based on the Cumulative distribution with Jensen-Shannon divergence (CJS-CNN) is presented to predict the aesthetic score distribution of human ratings, with a new reliability-sensitive learning method based on the kurtosis of the score distribution, which eliminates the requirement of the original full data of human ratings (without normalization).

Privacy Preserving Face Retrieval in the Cloud for Mobile Users

no code implementations9 Aug 2017 Xin Jin, Shiming Ge, Chenggen Song

The experimental results reveal that our protocol can successfully retrieve the proper photos from the cloud server and protect the user photos and the face detector.

Privacy Preserving Retrieval

Detecting Masked Faces in the Wild With LLE-CNNs

no code implementations CVPR 2017 Shiming Ge, Jia Li, Qiting Ye, Zhao Luo

Detecting masked faces (i. e., faces with occlusions) is a challenging task due to two main reasons: 1)the absence of large datasets of masked faces, and 2)the absence of facial cues from the masked regions.

ILGNet: Inception Modules with Connected Local and Global Features for Efficient Image Aesthetic Quality Classification using Domain Adaptation

2 code implementations7 Oct 2016 Xin Jin, Le Wu, Xiao-Dong Li, Xiaokun Zhang, Jingying Chi, Siwei Peng, Shiming Ge, Geng Zhao, Shuying Li

Thus, it is easy to use a pre-trained GoogLeNet for large-scale image classification problem and fine tune our connected layers on an large scale database of aesthetic related images: AVA, i. e. \emph{domain adaptation}.

Aesthetics Quality Assessment Domain Adaptation +2

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