-
Hello,
In your opinion, what is the best way to distill a large vision transformer (eg. ViT-g) into a small one (eg. ViT-B) ?
Seems there are many alternatives: MIM as for EVA, distillation toke…
-
Dear authors,
Thank you for your excellent work. However, I have some problems reproducing your experimental results for the baseline KD [21]. The result of KD on Cora is 77.63% rather than 83.2%. …
-
The performance for LSP in lab_knowledge_distillation is much less than results reported in paper.
Actually, this descrease is caused by GATConv in DGL.
In the source code:
，大家是否已经迫不及待了呢~
为了帮助大…
-
Hi, compared to the newest performance of yolor, yolov7 is still a little lower on mAP.
Tested on img-szie=1280, yolor-d6 mAP is 58.2%, and yolov7-e6e mAP is 56.8%.
Are there some strong training tr…
-
https://arxiv.org/abs/1910.01108
-
The follow-up research from PaLM switched in Flan-PaLM to the encoder-decoder t5 architecture. How would it be possible to also add an encoder to this implementation?