Back to Search

Generalization to unseen viewpoint images of objects via alleviated pose attentive capsule agreement

Title	Generalization to unseen viewpoint images of objects via alleviated pose attentive capsule agreement
Author	Özcan, Barış, Kınlı, Osman Furkan, Kıraç, Mustafa Furkan
Publication Date:	2023-02
Publication Place	- Springer
Subject	Capsule networks, Neural networks, Novel viewpoint generalization, Quaternion neural networks
Type	Periodical
Language	English
Digital	Yes
Manuscript	No
Library:	Özyeğin University
Library Asset ID	0941-0643
Record ID	48c369a5-2c01-40ee-bc52-da9e5073184f
Library Location	Computer Science
Date	2023-02
Sample Text	Despite their achievements in object recognition, Convolutional Neural Networks (CNNs) particularly fail to generalize to unseen viewpoints of a learned object even with substantial samples. On the other hand, recently emerged capsule networks outperform CNNs in novel viewpoint generalization tasks even with significantly fewer parameters. Capsule networks group the neuron activations for representing higher level attributes and their interactions for achieving equivariance to visual transformations. However, capsule networks have a high computational cost for learning the interactions of capsules in consecutive layers via the, so called, routing algorithm. To address these issues, we propose a novel routing algorithm, Alleviated Pose Attentive Capsule Agreement (ALPACA) which is tailored for capsules that contain pose, feature and existence probability information together to enhance novel viewpoint generalization of capsules on 2D images. For this purpose, we have created a Novel ViewPoint Dataset (NVPD) a viewpoint-controlled texture-free dataset that has 8 different setups where training and test samples are formed by different viewpoints. In addition to NVPD, we have conducted experiments on iLab2M dataset where the dataset is split in terms of the object instances. Experimental results show that ALPACA outperforms its capsule network counterparts and state-of-the-art CNNs on iLab2M and NVPD datasets. Moreover, ALPACA is 10 times faster when compared to routing-based capsule networks. It also outperforms attention-based routing algorithms of the domain while keeping the inference and training times comparable. Lastly, our code, the NVPD dataset, test setups, and implemented models are freely available at https://github.com/Boazrciasn/ALPACA.
DOI	10.1007/s00521-022-07900-3
Cilt	35

View in source Özyeğin University Özyeğin University - Historical works, archives, and periodicals search engine

Özyeğin University

Generalization to unseen viewpoint images of objects via alleviated pose attentive capsule agreement

Author Özcan, Barış, Kınlı, Osman Furkan, Kıraç, Mustafa Furkan

Publication Date 2023-02

Publication Place - Springer

Subject Capsule networks, Neural networks, Novel viewpoint generalization, Quaternion neural networks

Type Periodical

Language English

Digital Yes

Manuscript No

Library Özyeğin University

Library Asset ID 0941-0643

Record ID 48c369a5-2c01-40ee-bc52-da9e5073184f

Library Location Computer Science

Date 2023-02

Sample Text Despite their achievements in object recognition, Convolutional Neural Networks (CNNs) particularly fail to generalize to unseen viewpoints of a learned object even with substantial samples. On the other hand, recently emerged capsule networks outperform CNNs in novel viewpoint generalization tasks even with significantly fewer parameters. Capsule networks group the neuron activations for representing higher level attributes and their interactions for achieving equivariance to visual transformations. However, capsule networks have a high computational cost for learning the interactions of capsules in consecutive layers via the, so called, routing algorithm. To address these issues, we propose a novel routing algorithm, Alleviated Pose Attentive Capsule Agreement (ALPACA) which is tailored for capsules that contain pose, feature and existence probability information together to enhance novel viewpoint generalization of capsules on 2D images. For this purpose, we have created a Novel ViewPoint Dataset (NVPD) a viewpoint-controlled texture-free dataset that has 8 different setups where training and test samples are formed by different viewpoints. In addition to NVPD, we have conducted experiments on iLab2M dataset where the dataset is split in terms of the object instances. Experimental results show that ALPACA outperforms its capsule network counterparts and state-of-the-art CNNs on iLab2M and NVPD datasets. Moreover, ALPACA is 10 times faster when compared to routing-based capsule networks. It also outperforms attention-based routing algorithms of the domain while keeping the inference and training times comparable. Lastly, our code, the NVPD dataset, test setups, and implemented models are freely available at https://github.com/Boazrciasn/ALPACA.

DOI 10.1007/s00521-022-07900-3

Cilt 35