Results 271 to 280 of about 3,080,648 (304)
Some of the next articles are maybe not open access.
Generalization Self-distillation with Epoch-wise Regularization
2021 International Joint Conference on Neural Networks (IJCNN), 2021Recent advances in deep neural network have achieved remarkable successes in various computer vision tasks. However, deep neural network with millions of parameters may suffer from poor generalization due to overfitting. To improve the generalization performance, many methods have been proposed such as data augmentation, label smoothing and knowledge ...
Yuelong Xia, Yun Yang 0003
openaire +1 more source
Tolerant Self-Distillation for image classification
Neural NetworksDeep neural networks tend to suffer from the overfitting issue when the training data are not enough. In this paper, we introduce two metrics from the intra-class distribution of correct-predicted and incorrect-predicted samples to provide a new perspective on the overfitting issue.
Mushui Liu +4 more
openaire +2 more sources
Probabilistic online self-distillation
Neurocomputing, 2022Maria Tzelepi +2 more
openaire +1 more source
Restructuring the Teacher and Student in Self-Distillation
IEEE Transactions on Image ProcessingKnowledge distillation aims to achieve model compression by transferring knowledge from complex teacher models to lightweight student models. To reduce reliance on pre-trained teacher models, self-distillation methods utilize knowledge from the model itself as additional supervision.
Yujie Zheng +5 more
openaire +2 more sources
SSSD: Self-Supervised Self Distillation
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023Wei-Chi Chen, Wei-Ta Chu
openaire +1 more source
Image classification based on self-distillation
Applied Intelligence, 2022Yuting Li +4 more
openaire +1 more source
Weighted self Distillation for Chinese word segmentation
Findings of the Association for Computational Linguistics: ACL 2022, 2022Rian He +3 more
openaire +1 more source
Future Augmentation with Self-distillation in Recommendation
2023Chong Liu +8 more
openaire +1 more source
Self-Distillation: Towards Efficient and Compact Neural Networks
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021Linfeng Zhang, Kaisheng Ma
exaly
Diversified branch fusion for self-knowledge distillation
Information Fusion, 2023Fuyan Ma, Bin Sun, Mingkui Tan
exaly