Multi-view contrastive learning for online knowledge distillation
Previous Online Knowledge Distillation (OKD) often carries out mutually exchanging
probability distributions, but neglects the useful representational knowledge. We there-fore …
probability distributions, but neglects the useful representational knowledge. We there-fore …
When To Grow? A Fitting Risk-Aware Policy for Layer Growing in Deep Neural Networks
Neural growth is the process of growing a small neural network to a large network and has
been utilized to accelerate the training of deep neural networks. One crucial aspect of neural …
been utilized to accelerate the training of deep neural networks. One crucial aspect of neural …
Remote sensing image scene classification by multiple granularity semantic learning
W Guo, S Li, J Yang, Z Zhou, Y Liu, J Lu… - IEEE Journal of …, 2022 - ieeexplore.ieee.org
Remote sensing image scene classification faces challenges, such as the difference in
semantic granularity of different scene categories and the imbalance of the number of …
semantic granularity of different scene categories and the imbalance of the number of …
Towards efficient convolutional network models with filter distribution templates
R Izquierdo-Cordova, W Mayol-Cuevas - arXiv preprint arXiv:2104.08446, 2021 - arxiv.org
Increasing number of filters in deeper layers when feature maps are decreased is a widely
adopted pattern in convolutional network design. It can be found in classical CNN …
adopted pattern in convolutional network design. It can be found in classical CNN …