HackerPapers

arXiv:1710.09829cs.CV

Dynamic Routing Between Capsules

Sara Sabour, Nicholas Frosst, Geoffrey E Hinton

Abstract

A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity such as an object or an object part. We use the length of the activity vector to represent the probability that the entity exists and its orientation to represent the instantiation parameters. Active capsules at one level make predictions, via transformation matrices, for the instantiation parameters of higher-level capsules. When multiple predictions agree, a higher level capsule becomes active. We show that a discrimininatively trained, multi-layer capsule system achieves state-of-the-art performance on MNIST and is considerably better than a convolutional net at recognizing highly overlapping digits. To achieve these results we use an iterative routing-by-agreement mechanism: A lower-level capsule prefers to send its output to higher level capsules whose activity vectors have a big scalar product with the prediction coming from the lower-level capsule.

arXiv comments
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition

On Hacker News

Linked by 14 identifiable commenters in 16 comments across 16 threads, from Oct 2017 to Feb 2023. Found in 5 HN submissions from Oct 2017 to Nov 2017. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments16 threads

  1. 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

  2. Explainable Deep Learning: A Field Guide for the Uninitiated 1 comment

    • I'm surprised there is no mention of capsules and capsule-routing algorithms. Capsules are groups of neurons that represent discrete entities in different contexts. For example, a 4x4 pose matrix is a capsule representing a particular object in different orientations seen from…

      cs702View on HNParent context

  3. A Differentiable Programming System to Bridge ML and Scientific Computing 1 comment

    • Keno: first of all, let me give a big public thank you to you and your colleagues. (For those here who don't know, Keno is listed as one of the authors of the paper, and works closely with Mike Innes, lead author and also lead developer of Zygote. Mike is also an active member…

      cs702View on HNParent context

  4. Machine learning systems are stuck in a rut 1 comment

    • Direct link to the Google Brain paper, which is well worth a read: https://dl.acm.org/citation.cfm?id=3321441 (click on "PDF" link to read) Abstract: "In this paper we argue that systems for numerical computing are stuck in a local basin of performance and programmability.…

      cs702View on HNParent context

  5. Why do CNNs generalize so poorly to small image transformations? 1 comment

    • You made me think of the Margaret Thatcher Illusion, for which the best example I found was Dr. Phil Plait[0]. Funny thing, the idea of Capsule Networks (Hinton et al)[1, 2] seems to tackle some of these issues, though it's they're a bit young yet and more more work. [0]…

      dr_zoidbergView on HNParent context

  6. Keras reimplementation of "One pixel attack for fooling deep neural networks" 1 comment

    • I wonder how well capsule networks could deal with this, considering they're more robust than traditional CNNs towards other sorts of adversarial attacks. My guess is that one-pixel changes are going to do very little to alter pose information (though they will still alter the…

      xvedejasView on HNParent context

  7. Brain Cells Share Information with Virus-Like Capsules 1 comment

    • Is the mechanism of 'Arc' gene related to the dynamic routing process of Capsule networks [1, 2]? [1] https://kndrck.co/posts/capsule_networks_explained/ [2] https://arxiv.org/abs/1710.09829

      babak_apView on HNParent context

  8. Ask HN: What was the best CS paper you read in 2017? 1 comment

    • Dynamic Routing Between Capsules the long awaited paper from Geoffrey Hinton (although Sara Sabour is principal author, Hinton has been hinting at this for a while now) on an alternative to back-propagation https://arxiv.org/abs/1710.09829

      leecarraherView on HNParent context

  9. Researchers create “neuromorphic chip” that is modeled after the brain 1 comment

    • I sympathize with this being in a similar professional situation and having once been introduced to this field via Hofstadter. His musings are usually on a distinctly symbolic level however, and though it is not my intention to defend a kind of results-only pragmatic approach, I…

      arketypView on HNParent context

  10. A Year in Computer Vision 1 comment

    • Capsule networks[1] have literally not been used on anything larger than what is considered a toy dataset for computer vision yet. Whilst there is potential there I'd argue it's too early to ascribe extreme levels of excitement towards it. [1]: https://arxiv.org/abs/1710.09829

      SmerityView on HNParent context

  11. Deep Learning Is Eating Software 1 comment

    • > 2% is HUGE at this point Hell, on MNIST 0.14% is huge. Geff Hinton created an entire new architecture to get 0.25% error, which is far better than the baseline 0.39% error [1]. To be fair, he did reduce the error by 35%. [1]:https://arxiv.org/pdf/1710.09829.pdf

      skierscottView on HNParent context

  12. Google A.I. researchers develop alternative architecture for neural networks 1 comment

    • This doesn’t add much on top of the Wired article. Lots of comments on that: https://news.ycombinator.com/item?id=15609402 Here’s the paper: https://arxiv.org/abs/1710.09829

      stablemapView on HNParent context

  13. A New Twist on Neural Networks 1 comment

    • The only thing is that, when this presentation was given, it seems they hadn't worked much more than MNIST (so the new thing now would be the toys-recognition net). The paper however details their experiments on Cifar-10 and other datasets in the discussion section. They don't…

      SophosQView on HNParent context

  14. Hinton's 'Capsule Networks' Unveiled 1 comment

    • To save you clicks, the two pre-prints are at : https://arxiv.org/pdf/1710.09829.pdf && https://openreview.net/pdf?id=HJWLfGWRb

      cbennettView on HNParent context

  15. Hinton proposes CapsNet 1 comment

    • The article discussed in the review is "Dynamic Routing Between Capsules": https://arxiv.org/abs/1710.09829

      grzmView on HNParent context

  16. RCN is much more data efficient than traditional Deep Neural Networks 1 comment

    • This is trueish, but there is more to it than that. It is true for sure that absolute performance on MNIST isn't the most interesting thing in the world. But when introducing a new tool or technique being able to show competitive performance on MNIST is a good way to show that…

      nlView on HNParent context

Submitted to Hacker News

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