paper-with-me

홈 › Papers

Group Equivariant Capsule Networks

2018-06-13 · NeurIPS 2018 12 · Jan Eric Lenssen, Matthias Fey, Pascal Libuschewski

We present group equivariant capsule networks, a framework to introduce guaranteed equivariance and invariance properties to the capsule network idea. Our work can be divided into two contributions. First, we present a generic routing by agreement algorithm defined on elements of a group and prove that equivariance of output pose vectors, as well as invariance of output activations, hold under certain conditions. Second, we connect the resulting equivariant capsule networks with work from the field of group convolutional networks. Through this connection, we provide intuitions of how both methods relate and are able to combine the strengths of both approaches in one deep neural network architecture. The resulting framework allows sparse evaluation of the group convolution operator, provides control over specific equivariance and invariance properties, and can use routing by agreement instead of pooling operations. In addition, it is able to provide interpretable and equivariant representation vectors as output capsules, which disentangle evidence of object existence from its pose.

📄 PDF Abstract BibTeX arXiv:1806.05086

Code (1)

mrjel/group_equivariant_capsules_pytorch 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Capsule Network A capsule is an activation vector that basically executes on its inputs some complex internal computations. Length of these activation vectors signifies the probability of…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Building Deep Equivariant Capsule Networks

2020-05-01 · ICLR 2020 1 · Sai Raam Venkataraman, S. Balasubramanian, R. Raghunatha Sarma

Capsule networks are constrained by the parameter-expensive nature of their layers, and the general lack of provable equivariance guarantees. We present a variation of capsule networks that aims to remedy this. We identi…

Building Deep, Equivariant Capsule Networks

2019-08-04 · Sairaam Venkatraman, S. Balasubramanian, R. Raghunatha Sarma

Capsule networks are constrained by the parameter-expensive nature of their layers, and the general lack of provable equivariance guarantees. We present a variation of capsule networks that aims to remedy this. We identi…

Navigating the Unseen: Zero-shot Scene Graph Generation via Capsule-Based Equivariant Features

2025-01-01 · CVPR 2025 1 · Wenhuan Huang, Yi Ji, Guiqian Zhu, Li Ying 외

In scene graph generation (SGG), the accurate prediction of unseen triples is essential for its effectiveness in downstream vision-language tasks. We hypothesize that the predicates of unseen triples can be viewed as…

AttributeGraph GenerationScene Graph GenerationZero-Shot Scene Graph Generation

Equivariant and Steerable Neural Networks: A review with special emphasis on the symmetric group

2023-01-08 · Patrick Krüger, Hanno Gottschalk

Convolutional neural networks revolutionized computer vision and natrual language processing. Their efficiency, as compared to fully connected neural networks, has its origin in the architecture, where convolutions refle…

speech-recognitionSpeech RecognitionTranslation

Grouping Capsules Based Different Types

2019-11-12 · Qiang Ren

Capsule network was introduced as a new architecture of neural networks, it encoding features as capsules to overcome the lacking of equivariant in the convolutional neural networks. It uses dynamic routing algorithm to …