Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Lan, Weichao"'
Knowledge distillation (KD) has become a widely used technique in the field of model compression, which aims to transfer knowledge from a large teacher model to a lightweight student model for efficient network development. In addition to the supervi
Externí odkaz:
http://arxiv.org/abs/2404.03693
The imbalanced distribution of long-tailed data presents a considerable challenge for deep learning models, as it causes them to prioritize the accurate classification of head classes but largely disregard tail classes. The biased decision boundary c
Externí odkaz:
http://arxiv.org/abs/2306.06963
It is not uncommon that real-world data are distributed with a long tail. For such data, the learning of deep neural networks becomes challenging because it is hard to classify tail classes correctly. In the literature, several existing methods have
Externí odkaz:
http://arxiv.org/abs/2305.10648
Unstructured pruning has the limitation of dealing with the sparse and irregular weights. By contrast, structured pruning can help eliminate this drawback but it requires complex criterion to determine which components to be pruned. To this end, this
Externí odkaz:
http://arxiv.org/abs/2205.01508
Autor:
Lan, Weichao, Lan, Liang
Deep Convolutional Neural Networks (CNN) have been successfully applied to many real-life problems. However, the huge memory cost of deep CNN models poses a great challenge of deploying them on memory-constrained devices (e.g., mobile phones). One po
Externí odkaz:
http://arxiv.org/abs/2010.02778
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
The imbalanced distribution of long-tailed data poses a challenge for deep neural networks, as models tend to prioritize correctly classifying head classes over others so that perform poorly on tail classes. The lack of semantics for tail classes is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::562cd1a1d779db333338b6e8c8a128d9
http://arxiv.org/abs/2306.06963
http://arxiv.org/abs/2306.06963
Autor:
Lan, Weichao, Lan, Liang
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:8235-8242
Deep Convolutional Neural Networks (CNN) have been successfully applied to many real-life problems. However, the huge memory cost of deep CNN models poses a great challenge of deploying them on memory-constrained devices (e.g., mobile phones). One po