111 citations · 275 across the 9 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CV2023
DOT: A Distillation-Oriented Trainer
Borui Zhao, Quan Cui, Renjie Song +1
Knowledge distillation transfers knowledge from a large model to a small one via task and distillation losses. In this paper, we observe a trade-off between task and distillation l…
cs.CV2023★ 3 cited
Vision Learners Meet Web Image-Text Pairs
Bingchen Zhao, Quan Cui, Hao Wu +3
Many self-supervised learning methods are pre-trained on the well-curated ImageNet-1K dataset. In this work, given the excellent scalability of web data, we consider self-supervise…