Hong-Yu Zhou, Chixiang Lu, Sibei Yang, Yizhou Yu. ConvNets vs. Transformers: Whose Visual Representations are More Transferable?. In IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021, Montreal, BC, Canada, October 11-17, 2021. pages 2230-2238, IEEE, 2021. [doi]
Abstract is missing.