DeepAI AI Chat
Log In Sign Up

PatchVAE: Learning Local Latent Codes for Recognition

by   Kamal Gupta, et al.
University of Maryland

Unsupervised representation learning holds the promise of exploiting large amounts of unlabeled data to learn general representations. A promising technique for unsupervised learning is the framework of Variational Auto-encoders (VAEs). However, unsupervised representations learned by VAEs are significantly outperformed by those learned by supervised learning for recognition. Our hypothesis is that to learn useful representations for recognition the model needs to be encouraged to learn about repeating and consistent patterns in data. Drawing inspiration from the mid-level representation discovery work, we propose PatchVAE, that reasons about images at patch level. Our key contribution is a bottleneck formulation that encourages mid-level style representations in the VAE framework. Our experiments demonstrate that representations learned by our method perform much better on the recognition tasks compared to those learned by vanilla VAEs.


page 1

page 6

page 7

page 12


Unsupervised Learning of View-invariant Action Representations

The recent success in human action recognition with deep learning method...

Improving VAE-based Representation Learning

Latent variable models like the Variational Auto-Encoder (VAE) are commo...

Unsupervised Learning of Neurosymbolic Encoders

We present a framework for the unsupervised learning of neurosymbolic en...

Unsupervised Representation Learning For Context of Vocal Music

In this paper we aim to learn meaningful representations of sung intonat...

Unsupervisedly Learned Representations: Should the Quest be Over?

There exists a Classification accuracy gap of about 20 methods of genera...

Laplacian Denoising Autoencoder

While deep neural networks have been shown to perform remarkably well in...

Topological Neural Discrete Representation Learning à la Kohonen

Unsupervised learning of discrete representations from continuous ones i...

Code Repositories


PyTorch implementation of "PatchVAE: Learning Local Latent Codes for Recognition" to appear in CVPR 2020

view repo