论文笔记_A Large-Scale Car Dataset for Fine-Grained Categorization and Verification

CompCars是一个大型汽车数据集,包含多种视角、汽车部件和丰富属性。它用于汽车模型分类、验证和属性预测。数据集由监控和网络图像组成,涵盖1716个车型,标记有视角、部件和各种属性。实验包括使用预训练的Overfeat模型进行细粒度分类、属性预测和车辆验证。
摘要由CSDN通过智能技术生成

网址:http://mmlab.ie.cuhk.edu.hk/datasets/comp_cars/index.html
论文地址:https://arxiv.org/abs/1506.08959 arXiv:1506.08959, 2015
作者:
Linjie Yang
Ping Luo http://personal.ie.cuhk.edu.hk/~pluo/
Chen Change Loy http://personal.ie.cuhk.edu.hk/~ccloy/publication.html
Xiaoou Tang

Model@Caffe
This model obtains a top-1 accuracy 91.2% and a top-5 accuracy 98.1% on the testing set, using only the center crop.

简介:
A large-scale dataset “CompCars”, covers not only diffferent car views, but also their different internal and external parts, and rich attributes.
The dataset is constructed with a cross-modality nature, containing a surveillance-nature and a web-nature set.

Applications: car model classification, car model verification, and attribute prediction.

Car verification, which targets at verifying whether two cars
belong to the same model, is an interesting and under researched problem.

Containing

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值