Stacked What-Where Auto-encoders
Junbo Zhao, Michael Mathieu, Ross Goroshin, Yann LeCun Courant Institute of Mathematical Sciences, New York University 719 Broadway, 12th Floor, New York, NY 10003 {junbo.zhao, mathieu, goroshin,
Abstract
We present a novel architecture, the “stacked what-where auto-encoders” (SWWAE), which integrates discriminative and generative pathways and provides a unified approach to supervised, semi-supervised and unsupervised learning without relying on sampling during training. An instantiation of SWWAE uses a convolutional net (Convnet) (LeCun et al. (1998)) to encode the input, and employs a deconvolutional net (Deconvnet) (Zeiler et al. (2010)) to produce the reconstruction. The objective function includes reconstruction terms that induce the hidden states in the Deconvnet to be similar to those of the Convnet. Each pooling layer produces two sets of variables: the “what” which are fed to the next layer, and its complementary variable “where” that are fed to the corresponding layer in the generative decoder.
中文速览
卷积神经网络的池化层在提升特征不变性的同时会丢掉位置信息，导致编码器和解码器之间出现信息不对称，传统方法只能靠采样来"脑补"这部分缺失——这既影响重建质量，也让大规模训练变得低效。本文提出"堆叠式 what-where 自编码器"（Stacked What-Where Auto-Encoders，SWWAE），核心思路是在每个池化层把输出拆成两份：记录"是什么"的最大值（what）沿编码器向上传递，记录"在哪里"的位置开关（where）通过横向连接直接送给对应的解码层，从而让解码器在无需采样的情况下精确重建输入。整个系统由卷积网络（编码）与反卷积网络（解码）联合端到端训练，只需调整损失权重便可在有监督、无监督和半监督三种模式之间无缝切换，本质上就是一次普通的反向传播。实验表明，SWWAE 在图像分类和特征可视化上均达到有竞争力的结果，且半监督设置下利用无标注数据可显著提升性能，为同一架构统一三种学习范式提供了简洁而实用的解决方案。
原文 arXiv:1506.02351;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1506.02351v8