1 code implementation • 7 Aug 2023 • Xinda Liu, Yaohui Zhu, Linhu Liu, Jiang Tian, Lili Wang
As the similar contents of the two views are salient or highly responsive in the feature map, the proposed FeaSC uses a response-aware scheme to localize salient features in an unsupervised manner.
no code implementations • 14 Jul 2021 • Xinda Liu, Lili Wang, Xiaoguang Han
In this paper, we analyze the difficulties of fine-grained image recognition from a new perspective and propose a transformer architecture with the peak suppression module and knowledge guidance module, which respects the diversification of discriminative features in a single image and the aggregation of discriminative clues among multiple images.
Ranked #6 on Fine-Grained Image Classification on Stanford Dogs
Fine-Grained Image Classification Fine-Grained Image Recognition