Yiting (Ethan) Li

Yiting (Ethan) Li

Vibing and Coding

Posts by Tags

Computer Vision

Empirical Studies on Capsule Network Representation and Improvements

2 minute read

Published:

Capsule networks is a novel approach showing promising results on SmallNorb and MNIST. Here we reproduce and build upon the impressive results shown by Sara Sabour et al. We experiment on the Capsule Network architecture by visualizing exactly what the capsules on different layers represents, what information they store about 3D objects in an image, and try to improve its classification results on CIFAR10 and SmallNorb with various methods including some tricks with reconstruction loss. Further, We present a deconvolution-based reconstruction module that reduces the number of learnable parameters by 80% from the fully-connected module presented by Sara Sabour et al.

Machine Learning

Empirical Studies on Capsule Network Representation and Improvements

2 minute read

Published:

Capsule networks is a novel approach showing promising results on SmallNorb and MNIST. Here we reproduce and build upon the impressive results shown by Sara Sabour et al. We experiment on the Capsule Network architecture by visualizing exactly what the capsules on different layers represents, what information they store about 3D objects in an image, and try to improve its classification results on CIFAR10 and SmallNorb with various methods including some tricks with reconstruction loss. Further, We present a deconvolution-based reconstruction module that reduces the number of learnable parameters by 80% from the fully-connected module presented by Sara Sabour et al.

Research

Empirical Studies on Capsule Network Representation and Improvements

2 minute read

Published:

Capsule networks is a novel approach showing promising results on SmallNorb and MNIST. Here we reproduce and build upon the impressive results shown by Sara Sabour et al. We experiment on the Capsule Network architecture by visualizing exactly what the capsules on different layers represents, what information they store about 3D objects in an image, and try to improve its classification results on CIFAR10 and SmallNorb with various methods including some tricks with reconstruction loss. Further, We present a deconvolution-based reconstruction module that reduces the number of learnable parameters by 80% from the fully-connected module presented by Sara Sabour et al.