Related references
Note: Only part of the references are listed.
Proceedings Paper
Computer Science, Artificial Intelligence
Scalable Vision Transformers with Hierarchical Pooling
Zizheng Pan et al.
Summary: The proposed Hierarchical Visual Transformer (HVT) progressively pools visual tokens to reduce sequence length and computational cost, outperforming competitive baselines on ImageNet and CIFAR-100 datasets without introducing extra complexity. HVT enhances model capacity by scaling dimensions and showcasing improved scalability in image classification tasks.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Channel Pruning for Accelerating Very Deep Neural Networks
Yihui He et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)