Yushi Yao, Chang Ye, Junfeng He, Gamaleldin F. Elsayed. Teacher-generated spatial-attention labels boost robustness and accuracy of contrastive models. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023. pages 23282-23291, IEEE, 2023. [doi]
Abstract is missing.