HackerPapers

arXiv:1511.06434cs.LG

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Alec Radford, Luke Metz, Soumith Chintala

Abstract

In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between the success of CNNs for supervised learning and unsupervised learning. We introduce a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrate that they are a strong candidate for unsupervised learning. Training on various image datasets, we show convincing evidence that our deep convolutional adversarial pair learns a hierarchy of representations from object parts to scenes in both the generator and discriminator. Additionally, we use the learned features for novel tasks - demonstrating their applicability as general image representations.

arXiv comments
Under review as a conference paper at ICLR 2016
Journal reference
DOI
Subjects
cs.LGMachine Learning cs.CVComputer Vision and Pattern Recognition

On Hacker News

Linked by 10 identifiable commenters in 10 comments across 9 threads, from Dec 2015 to Sep 2023. Found in 2 HN submissions from Nov 2015 to Jul 2026. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments9 threads

  1. What OpenAI really wants 1 comment

    • i highlighted this last night which seems to be making the rounds - https://twitter.com/swyx/status/1699369076529971545 Alec's CV (https://www.linkedin.com/in/alecradford/) seems to be: - 2011-2016 BSc Eng from Olin College - 2013+ started a data/AI consultancy as a sophomore…

      swyxView on HNParent context

  2. Ask HN: What were the papers on the list Ilya Sutskever gave John Carmack? 1 comment

    • I posted a list of papers on twitter, and will be posting a summary for each of them as well. here is the list https://twitter.com/vrungta/status/1623343807227105280 Unlocking the Secrets of AI: A Journey through the Foundational Papers by @vrungta (2023) 1. "Attention is All…

      vikashrungtaView on HNParent context

  3. When not to use deep learning 1 comment

    • Geoff Hinton refers to thought vectors performing reasoning by analogy using algebra [1] in his Royal Society Lecture. The other widely reported vector algebras in a semantic space were discovered by Mikolov et al when producing ~300 dimensional vectors for a billion word…

      deepnetView on HNParent context

  4. Generative Models 1 comment
  5. Blade Runner re-encoded using neural networks 1 comment

    • > But what's the point? Autoencoders don't really have much practical use now, but that's not the point of them. The point is we really want to figure out how to do unsupervised learning well and autoencoders are one of the few ways of doing it. We want to do unsupervised…

      zodiacView on HNParent context

  6. Technologists have produced a 3D-printed painting in the style of Rembrandt 1 comment

    • I'm guessing recent progress in texture synthesis [1] and content generation [2] using deep convolutional nets made this possible. It would be interesting to see what was actually fed into the generating system. That would be a piece of art truly speaking magnitudes. [1]…

      arketypView on HNParent context

  7. Tensorflow Implementation of Deep Visual Analogy-Making 1 comment

    • I don't speak with any authority on this. With word2vec you can do operations like king - man + woman and the nearest vector will be queen. Similarly capital cities will be in a similar relationship to their countries so if you take Rome - Italy + Spain you will be nearest to…

      jkldotioView on HNParent context

  8. Yann LeCun's comment on AlphaGo and true AI 1 comment

    • (1) Adversarial learning is unsupervised and works great. Most of language modeling is unsupervised (you predict next word, but it's not real supervision because it's self-supervision). There're many works in computer vision which are unsupervised and still give more or less…

      Sergej-ShegurinView on HNParent context

  9. Ask HN: Papers you read in 2015? 2 comments

    • One weird trick for parallelizing ConvNets: http://arxiv.org/abs/1404.5997 Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks: http://arxiv.org/abs/1511.06434 A Neural Network of Artistic Style: http://arxiv.org/abs/1508.06576

      temuzeView on HNParent context

    • I've been trying to read a paper a day since midsummer. These are a few of the interesting, for me personally, since then: Generating Sequences With Recurrent Neural Networks - http://arxiv.org/abs/1308.0850 Older one, but important to understand deeply since other recent ideas…

      nrmnView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.