【CVPR 2021】自我知识蒸馏:Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification

论文地址:

https://arxiv.org/abs/2104.13298

代码地址:

https://github.com/yxgeee/BAKE

主要问题:

知识蒸馏通常通过整合来自多个教师模型或学生模型(或者额外的分支)的“暗知识”并生成更好的软目标用来训练,但是往往需要以更多的计算量或参数量为代价

主要思路:

在这篇文章中,作者提出了Batch知识集成(BAKE),通过在同一小批中传播和集成其他样本的知识,来为锚定图像生成精细的软目标

在这里插入图片描述

具体来说就是对于每个感兴趣的样本,知识的传播根据一个Batch的样本间的相似度进行加权,这是根据当前网络动态估计的,因此传播的知识可以浓缩成更好的蒸馏软目标,通过这种方式,BAKE 框架实现了在只有一个网络的多个样本之间的在线知识集成,从而大大

  • 1
    点赞
  • 3
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论
Training deep models for lane detection is challenging due to the very subtle and sparse supervisory signals in- herent in lane annotations. Without learning from much richer context, these models often fail in challenging sce- narios, e.g., severe occlusion, ambiguous lanes, and poor lighting conditions. In this paper, we present a novel knowl- edge distillation approach, i.e., Self Attention Distillation (SAD), which allows a model to learn from itself and gains substantial improvement without any additional supervision or labels. Specifically, we observe that attention maps ex- tracted from a model trained to a reasonable level would encode rich contextual information. The valuable contex- tual information can be used as a form of ‘free’ supervision for further representation learning through performing top- down and layer-wise attention distillation within the net- work itself. SAD can be easily incorporated in any feed- forward convolutional neural networks (CNN) and does not increase the inference time. We validate SAD on three pop- ular lane detection benchmarks (TuSimple, CULane and BDD100K) using lightweight models such as ENet, ResNet- 18 and ResNet-34. The lightest model, ENet-SAD, per- forms comparatively or even surpasses existing algorithms. Notably, ENet-SAD has 20 × fewer parameters and runs 10 × faster compared to the state-of-the-art SCNN [16], while still achieving compelling performance in all bench- marks. Our code is available at https://github. com/cardwing/Codes-for-Lane-Detection.

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
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

打赏作者

BIT可达鸭

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

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