Dual Attention Networks for Few-Shot Fine-Grained Recognition

3 code implementations • Proceedings of the AAAI Conference on Artificial Intelligence 2022 • Shu-Lin Xu, Faen Zhang, Xiu-Shen Wei, Jianhua Wang

Specifically, by producing attention guidance from deep activations of input images, our hard-attention is realized by keeping a few useful deep descriptors and forming them as a bag of multi-instance learning.

Hard Attention Meta-Learning