Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Zeng, Boheng"'
We revisit the relationship between attention mechanisms and large kernel ConvNets in visual transformers and propose a new spatial attention named Large Kernel Convolutional Attention (LKCA). It simplifies the attention operation by replacing it wit
Externí odkaz:
http://arxiv.org/abs/2401.05738
Due to the gap between a substitute model and a victim model, the gradient-based noise generated from a substitute model may have low transferability for a victim model since their gradients are different. Inspired by the fact that the decision bound
Externí odkaz:
http://arxiv.org/abs/2303.05719
Autor:
Long, Yuyang, Zhang, Qilong, Zeng, Boheng, Gao, Lianli, Liu, Xianglong, Zhang, Jian, Song, Jingkuan
For black-box attacks, the gap between the substitute model and the victim model is usually large, which manifests as a weak attack performance. Motivated by the observation that the transferability of adversarial examples can be improved by attackin
Externí odkaz:
http://arxiv.org/abs/2207.05382
Autor:
Zeng Boheng
Publikováno v:
2022 19th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP).