Orthogonal Convolutional Neural Networks (CVPR 2020) - Crossminds
CrossMind.ai logo
Details
We develop an efficient approach to impose filter orthogonality on a convolutional layer. Our proposed orthogonal convolution requires no additional parameters and little computational overhead, and consistently outperforms the kernel orthogonality alternative on a wide range of tasks such as image classification and inpainting under supervised, semi-supervised and unsupervised settings. Project page: http://pwang.pw/ocnn.html
Comments
loading...
Reactions (0) | Note
    📝 No reactions yet
    Be the first one to share your thoughts!
loading...
Recommended