Towards the Characterization of Representations Learned via Capsule-based Network Architectures
Capsule Networks (CapsNets) have been re-introduced as a more compact and interpretable alternative to standard deep neural networks. While recent efforts have proved their compression capabilities, to date, their interpretability properties have not been fully assessed. Here, we conduct a systematic and principled study towards assessing the interpretability of these types of networks. Moreover, we pay special attention towards analyzing the level to which part-whole relationships are indeed encoded within the learned representation. Our analysis in the MNIST, SVHN, PASCAL-part and CelebA datasets suggest that the representations encoded in CapsNets might not be as disentangled nor strictly related to parts-whole relationships as is commonly stated in the literature.
Code (1)
Similar Papers 제목 키워드 기반
Generic Feature Learning for Wireless Capsule Endoscopy Analysis
The interpretation and analysis of the wireless capsule endoscopy recording is a complex task which requires sophisticated computer aided decision (CAD) systems in order to help physicians with the video screening and, f…
Distilling EEG Representations via Capsules for Affective Computing
Affective computing with Electroencephalogram (EEG) is a challenging task that requires cumbersome models to effectively learn the information contained in large-scale EEG signals, causing difficulties for real-time smar…
EEGElectroencephalogram (EEG)Knowledge DistillationVanishing Activations: A Symptom of Deep Capsule Networks
Capsule Networks, an extension to Neural Networks utilizing vector or matrix representations instead of scalars, were initially developed to create a dynamic parse tree where visual concepts evolve from parts to complete…
EquiCaps: Predictor-Free Pose-Aware Pre-Trained Capsule Networks
Learning self-supervised representations that are invariant and equivariant to transformations is crucial for advancing beyond traditional visual classification tasks. However, many methods rely on predictor architecture…
Pose EstimationOn Learning and Learned Data Representation by Capsule Networks
In this work, we investigate the following: 1) how the routing affects the CapsNet model fitting; 2) how the representation using capsules helps discover global structures in data distribution, and; 3) how the learned da…