Diffusion Probabilistic Models (DPMs) have shown a powerful capacity of generating high-quality image samples. Recently, diffusion autoencoders (Diff-AE) have been proposed to explore DPMs for representation learning via autoencoding. Their key idea is to jointly train an encoder for discovering meaningful representations from images and a conditional DPM as the decoder for reconstructing images. Considering that training DPMs from scratch will take a long time and there have existed numerous pre-trained DPMs, we propose \textbf{P}re-trained \textbf{D}PM \textbf{A}uto\textbf{E}ncoding (\textbf{PDAE}), a general method to adapt existing pre-trained DPMs to the decoders for image reconstruction, with better training efficiency and performance than Diff-AE. Specifically, we find that the reason that pre-trained DPMs fail to reconstruct an image from its latent variables is due to the information loss of forward process, which causes a gap between their predicted posterior mean and the true one. From this perspective, the classifier-guided sampling method can be explained as computing an extra mean shift to fill the gap, reconstructing the lost class information in samples. These imply that the gap corresponds to the lost information of the image, and we can reconstruct the image by filling the gap. Drawing inspiration from this, we employ a trainable model to predict a mean shift according to encoded representation and train it to fill as much gap as possible, in this way, the encoder is forced to learn as much information as possible from images to help the filling. By reusing a part of network of pre-trained DPMs and redesigning the weighting scheme of diffusion loss, PDAE can learn meaningful representations from images efficiently. Extensive experiments demonstrate the effectiveness, efficiency and flexibility of PDAE.


翻译:集成概率模型(DPMs) 显示了生成高质量图像样本的强大能力。 最近, 已经提议推广自动编码器( Diff- AE) 来探索 DPM, 以便通过自动编码学习 。 它们的关键想法是共同训练一个编码器, 以便从图像中发现有意义的表达方式, 并使用一个有条件的 DPM 来重建图像。 考虑到从头到尾培训DPM 将花费很长的时间, 并且已经有许多经过培训的DPM 。 我们提议 传播自动编码器( Diff- AE), 以便探索 DPM (Diff- AE) 以通过自动编码来进行演示 。 将现有的经培训过的DPM 改成图像重建的解析器, 培训效率和性能比 Diff- AE 重建的解析器要好。 具体地说, 我们发现, 预先训练过的DPMM 无法重建图像的隐含性变异性, 是因为信息过程会弥补, 导致预变的变异性, 的预变变变的变异性、 变变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 变 </s>

0
下载
关闭预览

相关内容

《计算机信息》杂志发表高质量的论文,扩大了运筹学和计算的范围,寻求有关理论、方法、实验、系统和应用方面的原创研究论文、新颖的调查和教程论文,以及描述新的和有用的软件工具的论文。官网链接:https://pubsonline.informs.org/journal/ijoc
NeurlPS 2022 | 自然语言处理相关论文分类整理
专知会员服务
48+阅读 · 2022年10月2日
自然语言处理顶会NAACL2022最佳论文出炉!
专知会员服务
42+阅读 · 2022年6月30日
100+篇《自监督学习(Self-Supervised Learning)》论文最新合集
专知会员服务
164+阅读 · 2020年3月18日
抢鲜看!13篇CVPR2020论文链接/开源代码/解读
专知会员服务
49+阅读 · 2020年2月26日
强化学习最新教程,17页pdf
专知会员服务
174+阅读 · 2019年10月11日
Hierarchically Structured Meta-learning
CreateAMind
26+阅读 · 2019年5月22日
Transferring Knowledge across Learning Processes
CreateAMind
27+阅读 · 2019年5月18日
强化学习的Unsupervised Meta-Learning
CreateAMind
17+阅读 · 2019年1月7日
Unsupervised Learning via Meta-Learning
CreateAMind
42+阅读 · 2019年1月3日
A Technical Overview of AI & ML in 2018 & Trends for 2019
待字闺中
16+阅读 · 2018年12月24日
disentangled-representation-papers
CreateAMind
26+阅读 · 2018年9月12日
vae 相关论文 表示学习 1
CreateAMind
12+阅读 · 2018年9月6日
国家自然科学基金
0+阅读 · 2014年12月31日
国家自然科学基金
0+阅读 · 2014年12月31日
国家自然科学基金
0+阅读 · 2013年12月31日
国家自然科学基金
0+阅读 · 2012年12月31日
国家自然科学基金
0+阅读 · 2012年12月31日
国家自然科学基金
0+阅读 · 2011年12月31日
Arxiv
16+阅读 · 2022年11月21日
Arxiv
29+阅读 · 2022年9月10日
Arxiv
14+阅读 · 2021年3月10日
VIP会员
相关基金
国家自然科学基金
0+阅读 · 2014年12月31日
国家自然科学基金
0+阅读 · 2014年12月31日
国家自然科学基金
0+阅读 · 2013年12月31日
国家自然科学基金
0+阅读 · 2012年12月31日
国家自然科学基金
0+阅读 · 2012年12月31日
国家自然科学基金
0+阅读 · 2011年12月31日
Top
微信扫码咨询专知VIP会员