Zobrazeno 1 - 10
of 1 321
pro vyhledávání: '"ZENG, Dan"'
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
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
Recognizing objects in low-resolution images is a challenging task due to the lack of informative details. Recent studies have shown that knowledge distillation approaches can effectively transfer knowledge from a high-resolution teacher model to a l
Externí odkaz:
http://arxiv.org/abs/2409.02555
While deep models have proved successful in learning rich knowledge from massive well-annotated data, they may pose a privacy leakage risk in practical deployment. It is necessary to find an effective trade-off between high utility and strong privacy
Externí odkaz:
http://arxiv.org/abs/2409.02404
Recently, the surge in the adoption of single-stream architectures utilizing pre-trained ViT backbones represents a promising advancement in the field of generic visual tracking. By integrating feature extraction and fusion into a cohesive framework,
Externí odkaz:
http://arxiv.org/abs/2407.05383
Empowered by transformer-based models, visual tracking has advanced significantly. However, the slow speed of current trackers limits their applicability on devices with constrained computational resources. To address this challenge, we introduce ABT
Externí odkaz:
http://arxiv.org/abs/2406.08037
Recent studies have suggested frequency-domain Data augmentation (DA) is effec tive for time series prediction. Existing frequency-domain augmentations disturb the original data with various full-spectrum noises, leading to excess domain gap between
Externí odkaz:
http://arxiv.org/abs/2405.16456
Masked face recognition is important for social good but challenged by diverse occlusions that cause insufficient or inaccurate representations. In this work, we propose a unified deep network to learn generative-to-discriminative representations for
Externí odkaz:
http://arxiv.org/abs/2405.16761
Evaluating the performance of Multi-modal Large Language Models (MLLMs), integrating both point cloud and language, presents significant challenges. The lack of a comprehensive assessment hampers determining whether these models truly represent advan
Externí odkaz:
http://arxiv.org/abs/2404.14678
Autor:
Githinji, P. Bilha, Yuan, Xi, Chen, Zhenglin, Gul, Ijaz, Shang, Dingqi, Liang, Wen, Deng, Jianming, Zeng, Dan, yu, Dongmei, Yan, Chenggang, Qin, Peiwu
Realizing sufficient separability between the distributions of healthy and pathological samples is a critical obstacle for pathology detection convolutional models. Moreover, these models exhibit a bias for contrast-based images, with diminished perf
Externí odkaz:
http://arxiv.org/abs/2403.02307