按年被提到
20192019 · 2 次2026
视觉、语音与图像生成›ViT 与视觉新架构·arXiv:1911.00792 · cs.LG

An Algorithm for Routing Capsules in All Domains

Franz A. Heinsen · 2019
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2019-11-06 · 最近 2020-06-03
2不同的人
4活跃月份
4讨论串
4被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Building on recent work on capsule networks, we propose a new, general-purpose form of "routing by agreement" that activates output capsules in a layer as a function of their net benefit to use and net cost to ignore input capsules from earlier layers. To illustrate the usefulness of our routing algorithm, we present two capsule networks that apply it in different domains: vision and language. The first network achieves new state-of-the-art accuracy of 99.1% on the smallNORB visual recognition task with fewer parameters and an order of magnitude less training than previous capsule models, and we find evidence that it learns to perform a form of "reverse graphics." The second network achieves new state-of-the-art accuracies on the root sentences of the Stanford Sentiment Treebank: 58.5% on fine-grained and 95.6% on binary labels with a single-task model that routes frozen embeddings from a pretrained transformer as capsules. In both domains, we train with the same regime. Code is available at https://github.com/glassroom/heinsen_routing along with replication instructions.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论cs702 · 2019-12

“I recently saw a paper (which I reposted here on HN a while back) that perhaps could help with your problem. The paper proposes an approach that sort of induces models to learn representations of objects that are good at predicting "the most agreed-upon" rotations of the inputs. I'm not explaining it well. Anyway, a model in the paper achieved SOTA on a c…”

Object-recognition dataset stumped the world’s best computer vision models原评论 ↗
评论cs702 · 2020-05

“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 different viewpoints. Similarly, a subword embedding can be seen as a capsule …”

Explainable Deep Learning: A Field Guide for the Uninitiated原评论 ↗
评论cs702 · 2020-06

“Have you looked at capsule-routing algorithms that use expectation-maximization to generate layer outputs in deep neural networks? For example, in https://research.google/pubs/pub46653/ and https://arxiv.org/abs/1911.00792 each output capsule in a layer is generated by a Gaussian mixture model and also has an associated "activation value" that increases t…”

Dirichlet Process Mixture Models in Pyro原评论 ↗
被提交为 story · 1 次