GiraffeDet的学习笔记

1 GiraffeDet模型

论文:GIRAFFEDET: A HEAVY-NECK PARADIGM FOR OBJECT DETECTION
代码:Github-GiraffeDet

2 GiraffeDet介绍

2.2 优点

适合scratch训练:

GiraffeDet模型适合 scratch training,原文是这样说的:

[GiraffeDet-paper]: Also under acceptable inference time, we observe that such a shallow GFPN (tiny) with a strong DCN backbone can improve the performance, and the performance has been largely increased with the growth of GFPN depth, as shown in Table 6. Note that as the design of GFPN, our GiraffeDet is more suitable for scratch training and has significant improvement.

评论
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