Zobrazeno 1 - 10
of 325
pro vyhledávání: '"Ge, Shiming"'
Federated learning is a distributed machine learning paradigm designed to protect data privacy. However, data heterogeneity across various clients results in catastrophic forgetting, where the model rapidly forgets previous knowledge while acquiring
Externí odkaz:
http://arxiv.org/abs/2411.03569
In practical scenarios, federated learning frequently necessitates training personalized models for each client using heterogeneous data. This paper proposes a backbone self-distillation approach to facilitate personalized federated learning. In this
Externí odkaz:
http://arxiv.org/abs/2409.15636
Interpreting the predictions of a black-box deep network can facilitate the reliability of its deployment. In this work, we propose a re-label distillation approach to learn a direct map from the input to the prediction in a self-supervision manner.
Externí odkaz:
http://arxiv.org/abs/2409.13137
Federated learning provides a privacy-preserving manner to collaboratively train models on data distributed over multiple local clients via the coordination of a global server. In this paper, we focus on label distribution skew in federated learning,
Externí odkaz:
http://arxiv.org/abs/2409.13136
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
Externí odkaz:
http://arxiv.org/abs/2409.12385
Autor:
Liu, Bochao, Lu, Jianghu, Wang, Pengju, Zhang, Junjie, Zeng, Dan, Qian, Zhenxing, Ge, Shiming
Deep learning models can achieve high inference accuracy by extracting rich knowledge from massive well-annotated data, but may pose the risk of data privacy leakage in practical deployment. In this paper, we present an effective teacher-student lear
Externí odkaz:
http://arxiv.org/abs/2409.12384
Deep trackers have proven success in visual tracking. Typically, these trackers employ optimally pre-trained deep networks to represent all diverse objects with multi-channel features from some fixed layers. The deep networks employed are usually tra
Externí odkaz:
http://arxiv.org/abs/2409.11785
Publikováno v:
IEEE TIP 2020
Face recognition in the wild is now advancing towards light-weight models, fast inference speed and resolution-adapted capability. In this paper, we propose a bridge distillation approach to turn a complex face model pretrained on private high-resolu
Externí odkaz:
http://arxiv.org/abs/2409.11786
Very low-resolution face recognition is challenging due to the serious loss of informative facial details in resolution degradation. In this paper, we propose a generative-discriminative representation distillation approach that combines generative r
Externí odkaz:
http://arxiv.org/abs/2409.06371
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.
Externí odkaz:
http://arxiv.org/abs/2409.05384