arXiv (Cornell University)· 2015· Preprint
Unsupervised Representation Learning with Deep Convolutional Generative\n Adversarial Networks
- 7,678citations
- 2015year
Short summary
Deep Convolutional Generative Adversarial Networks (DCGANs) with specific architectural constraints learn a hierarchy of image representations from object parts to scenes, applicable to novel tasks.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduces Deep Convolutional Generative Adversarial Networks (DCGANs) with specific architectural constraints.
- DCGANs demonstrate strong performance for unsupervised learning in image datasets.
- Learned representations capture a hierarchy from object parts to scenes.
- Features learned by DCGANs are applicable to novel tasks as general image representations.
AI-generated from the title and abstract; the full text is not read.
Abstract
In recent years, supervised learning with convolutional networks (CNNs) has\nseen huge adoption in computer vision applications. Comparatively, unsupervised\nlearning with CNNs has received less attention. In this work we hope to help\nbridge the gap between the success of CNNs for supervised learning and\nunsupervised learning. We introduce a class of CNNs called deep convolutional\ngenerative adversarial networks (DCGANs), that have certain architectural\nconstraints, and demonstrate that they are a strong candidate for unsupervised\nlearning. Training on various image datasets, we show convincing evidence that\nour deep convolutional adversarial pair learns a hierarchy of representations\nfrom object parts to scenes in both the generator and discriminator.\nAdditionally, we use the learned features for novel tasks - demonstrating their\napplicability as general image representations.\n
The authors' abstract, as published at the source. arXiv (Cornell University), 2015 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science