From f3d03c0e7311d1a77af02a00fdab1f5a871c9ebe Mon Sep 17 00:00:00 2001 From: YangYuqi317 <90373479+YangYuqi317@users.noreply.github.com> Date: Tue, 7 Feb 2023 09:36:29 +0800 Subject: [PATCH] Add files via upload --- configs/api_net/README.md | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 configs/api_net/README.md diff --git a/configs/api_net/README.md b/configs/api_net/README.md new file mode 100644 index 0000000..f7a8363 --- /dev/null +++ b/configs/api_net/README.md @@ -0,0 +1,13 @@ +# API-Net + +[API-Net](https://arxiv.org/abs/2002.10191) + +## Introduction + +In order to effectively identify contrastive clues among highly-confused categories, the writers propose a simple but effective Attentive Pairwise Interaction Network (API-Net), which can progressively recognize a pair of fine-grained images by interaction. They aim at learning a mutual vector first to capture semantic differences in the input pair, and then comparing this mutual vector with individual vectors to highlight their semantic differences respectively. Besides, they also introduce a score-ranking regularization to promote the priorities of these features. For more details, please refer to the [paper](https://arxiv.org/abs/2002.10191). + +## Framework +
+ +
+