Deep Energy: Using Energy Functions for Unsupervised Training of DNNs
Preprint
Abstract
The success of deep learning has been due in no small part to the availability of large annotated datasets. Thus, a major bottleneck in the current learning pipeline is the human annotation of data, which can be quite time consuming. For a given problem setting, we aim to circumvent this issue via the use of an externally specified energy function appropriate for that setting; we call this the "Deep Energy" approach. We show how to train a network on an entirely unlabelled dataset using such an energy function, and apply this general technique to learn CNNs for two specific tasks: seeded segmentation and image matting. Once the network parameters have been learned, we obtain a high-quality solution in a fast feed-forward style, without the need to repeatedly optimize the energy function for each image.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Deep Automatic Portrait Matting2016
- Single Image Dehazing via Multi-scale Convolutional Neural Networks2016
- Natural Image Matting Using Deep Convolutional Neural Networks2016
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution2016
- What’s the Point: Semantic Segmentation with Point Supervision2016
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- A Bayesian approach to digital matting2005
- Modeling Textures with Total Variation Minimization and Oscillating Patterns in Image ProcessingJournal of Scientific Computing, 2003
- Restoration of a single superresolution image from several blurred, noisy, and undersampled measured imagesIEEE Transactions on Image Processing, 1997
- A multiscale retinex for bridging the gap between color images and the human observation of scenesIEEE Transactions on Image Processing, 1997