BriefGPT.xyz
Oct, 2020
使用域外样本支持大规模图像识别
Supporting large-scale image recognition with out-of-domain samples
HTML
PDF
Christof Henkel, Philipp Singer
TL;DR
提出了一种高效的端到端方法,用于标注和排序地标图像,采用卷积神经网络将图像嵌入到高维特征空间,并使用视觉相似性分类图像,采用相似性重新排名预测,过滤噪声。使用该方法在2020年的Google地标识别挑战赛中获得了第一名。
Abstract
This article presents an efficient end-to-end method to perform
instance-level recognition
employed to the task of labeling and ranking
landmark images
. In a first step, we embed images in a high dimensional feat
→