Laplacian Denoising Autoencoder

by   Jianbo Jiao, et al.

While deep neural networks have been shown to perform remarkably well in many machine learning tasks, labeling a large amount of ground truth data for supervised training is usually very costly to scale. Therefore, learning robust representations with unlabeled data is critical in relieving human effort and vital for many downstream tasks. Recent advances in unsupervised and self-supervised learning approaches for visual data have benefited greatly from domain knowledge. Here we are interested in a more generic unsupervised learning framework that can be easily generalized to other domains. In this paper, we propose to learn data representations with a novel type of denoising autoencoder, where the noisy input data is generated by corrupting latent clean data in the gradient domain. This can be naturally generalized to span multiple scales with a Laplacian pyramid representation of the input data. In this way, the agent learns more robust representations that exploit the underlying data structures across multiple scales. Experiments on several visual benchmarks demonstrate that better representations can be learned with the proposed approach, compared to its counterpart with single-scale corruption and other approaches. Furthermore, we also demonstrate that the learned representations perform well when transferring to other downstream vision tasks.


page 2

page 3

page 5

page 6


Self-supervised regression learning using domain knowledge: Applications to improving self-supervised denoising in imaging

Regression that predicts continuous quantity is a central part of applic...

Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts

Self-supervised learning (SSL), as a newly emerging unsupervised represe...

Self-Supervised Pyramid Representation Learning for Multi-Label Visual Analysis and Beyond

While self-supervised learning has been shown to benefit a number of vis...

Rethinking Image Mixture for Unsupervised Visual Representation Learning

In supervised learning, smoothing label/prediction distribution in neura...

PatchVAE: Learning Local Latent Codes for Recognition

Unsupervised representation learning holds the promise of exploiting lar...

Autoencoder-augmented Neuroevolution for Visual Doom Playing

Neuroevolution has proven effective at many reinforcement learning tasks...

Topo2vec: Topography Embedding Using the Fractal Effect

Recent advances in deep learning have transformed many fields by introdu...

Please sign up or login with your details

Forgot password? Click here to reset