1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Superpixel Segmentation Via Convolutional Neural Networks With Regularized Information Maximization

Superpixel Segmentation Via Convolutional Neural Networks With Regularized Information Maximization

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

We propose an unsupervised superpixel segmentation method by optimizing a randomly-initialized convolutional neural network (CNN) in inference time. Our method generates superpixels via CNN from a single image without any labels by minimizing a proposed o

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Superpixel Segmentation Via Convolutional Neural Networks With Regularized Information Maximization

00:12:00

0 views

We propose an unsupervised superpixel segmentation method by optimizing a randomly-initialized convolutional neural network (CNN) in inference time. Our method generates superpixels via CNN from a single image without any labels by minimizing a proposed o

Superpixel Segmentation Via Convolutional Neural Networks With Regularized Information Maximization

00:00:00

0 views

We propose an unsupervised superpixel segmentation method by optimizing a randomly-initialized convolutional neural network (CNN) in inference time. Our method generates superpixels via CNN from a single image without any labels by minimizing a proposed o