Context Encoders: Feature Learning by Inpainting
| Autor: | Alexei A. Efros, Philipp Krähenbühl, Trevor Darrell, Deepak Pathak, Jeff Donahue |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Artificial Intelligence Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Inpainting Initialization Context (language use) 02 engineering and technology Convolutional neural network Machine Learning (cs.LG) Computer Science - Graphics 0202 electrical engineering electronic engineering information engineering Segmentation business.industry 020207 software engineering Pattern recognition Graphics (cs.GR) Visualization Computer Science - Learning Artificial Intelligence (cs.AI) 020201 artificial intelligence & image processing Artificial intelligence business Encoder Feature learning |
| Zdroj: | CVPR |
| DOI: | 10.48550/arxiv.1604.07379 |
| Popis: | We present an unsupervised visual feature learning algorithm driven by context-based pixel prediction. By analogy with auto-encoders, we propose Context Encoders -- a convolutional neural network trained to generate the contents of an arbitrary image region conditioned on its surroundings. In order to succeed at this task, context encoders need to both understand the content of the entire image, as well as produce a plausible hypothesis for the missing part(s). When training context encoders, we have experimented with both a standard pixel-wise reconstruction loss, as well as a reconstruction plus an adversarial loss. The latter produces much sharper results because it can better handle multiple modes in the output. We found that a context encoder learns a representation that captures not just appearance but also the semantics of visual structures. We quantitatively demonstrate the effectiveness of our learned features for CNN pre-training on classification, detection, and segmentation tasks. Furthermore, context encoders can be used for semantic inpainting tasks, either stand-alone or as initialization for non-parametric methods. Comment: New results on ImageNet Generation |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|