论文笔记 ——《Deep Domain Confusion: Maximizing for Domain Invariance》

本文介绍了一种增强深度网络迁移性的方法,通过最小化训练集上的分类误差和训练集与测试集之间的样本分布差异(MMD最大均值差异),有效避免了fine-tune带来的过拟合,取得了同类任务中最佳效果。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

论文笔记 ——《深度学习神经网络迁移性提升》(《Deep Domain Confusion: Maximizing for Domain Invariance》)

答主因为最近在看迁移学习的论文,时间比较紧张,所以这几篇论文就只抓一下大纲,不考虑具体细节和模拟了,权当是随手笔记了(为了防止BOSS抽查啥也想不起来-> ->),后面有时间会把细节补上的。

关键知识点

  1. 本文讲了一种新的CNN架构,目的在于找到自适应层尺寸和位置使距离最小,混淆最大(如图)
  2. MMD是用来刻画source domain和target domain差异的
  3. 迁移性可通过添加一个自适应层得到提升

在这里插入图片描述

贡献

  1. 作者提出了一种增强深度网络迁移性的方法,该方法通过在训练模型时,不仅最小化训练集上的分类误差,并且最小化训练集和测试集之间的样本分布差异(通过MMD最大均值差异)
  2. 该工作属于一种领域自适应(domain adaptation) 的方法,它能有效地抵御fine-tune所带来了过拟合,它当时在同类任务中取得了最好的效果。

算法

同时减小分类损失和训练集与测试集的分布差异,这可以转化为一个优化损失函数的问题。
损失函数如下:

模拟

作者利用MMD方法对自适应层的位置和尺寸进行了选择(但并没有精确给出原因)。

# DDC-transfer-learning A simple implementation of Deep Domain Confusion: Maximizing for Domain Invariance which is inspired by [transferlearning][https://github.com/jindongwang/transferlearning]. The project contains *Pytorch* code for fine-tuning *Alexnet* as well as *DDCnet* implemented according to the original paper which adds an adaptation layer into the Alexnet. The *office31* dataset used in the paper is also used in this implementation to test the performance of fine-tuning *Alexnet* and *DDCnet* with additional linear *MMD* loss. # Run the work * Run command `python alextnet_finetune.py` to fine-tune a pretrained *Alexnet* on *office31* dataset with *full-training*. * Run command `python DDC.py` to fine-tune a pretrained *Alexnet* on *office31* dataset with *full-training*. # Experiment Results Here we have to note that *full-training* protocol, which is taking all the samples from one domain as the source or target domain, and *dowm-sample* protocol, which is choosing 20 or 8 samples per category to use as the domain data, are quite different data preparation methods with different experiment results. | Methods | Results (amazon to webcame) | | :------: | :------: | | fine-tuning Alexnet (full-training) in *Pytorch* | Around 51% | | DDC ( pretrained Alexnet with adaptation layer and MMD loss) in *Pytorch* | Around 56% | # Future work - [ ] Write data loader using *down-sample* protocol mentioned in the paper instead of using *full-training* protocol. - [ ] Considering trying a tensorflow version to see if frameworks can have a difference on final experiment results. # Reference Tzeng E, Hoffman J, Zhang N, et al. Deep domain confusion: Maximizing for domain invariance[J]. arXiv preprint arXiv:1412.3474, 2014.
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