方法证据记录
Semi-supervised Vision Transformer
Semi-supervised Vision Transformer applies the patch-based self-attention architecture of ViT to settings where only a fraction of images are labeled, exploiting large unlabeled corpora through pseudo-labeling, consistency regularization, or self-supervised pretext tasks before fine-tuning on the small labeled set. This approach achieves near-supervised accuracy even when labeled images are scarce.
源记录
引文逐字复制自方法源记录。这些引文不代表任何层级的验证。
Semi-supervised Vision Transformer (Semi-supervised ViT)
分类方法记录 · ml-model / deep-learning
- Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. International Conference on Learning Representations (ICLR 2021). · URL
- Zhai, X., Kolesnikov, A., Houlsby, N., & Beyer, L. (2022). Scaling Vision Transformers. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12104–12113. · URL
精选声明
声明已持久化到证据分类账中，每个声明都有自己的评估。
尚无精选声明
当分类账中没有声明时，此视图不会自行创建声明评估。
相关方法
从方法图中生成，显示为机器建议的关系 — 不推断任何证据声明。