2 papers
cs.CV2022
ViT-P: Rethinking Data-efficient Vision Transformers from Locality
Bin Chen, Ran Wang, Di Ming +1
Recent advances of Transformers have brought new trust to computer vision tasks. However, on small dataset, Transformers is hard to train and has lower performance than convolution…
cs.CV2021
Deep Domain Adaptation for Pavement Crack Detection
Huijun Liu, Chunhua Yang, Ao Li +4
Deep learning-based pavement cracks detection methods often require large-scale labels with detailed crack location information to learn accurate predictions. In practice, however,…