Neural Similarity Learning
release_cm5o6xswgnbklnyjxf5wr4oc2a
by
Weiyang Liu, Zhen Liu, James M. Rehg, Le Song
2019
Abstract
Inner product-based convolution has been the founding stone of convolutional
neural networks (CNNs), enabling end-to-end learning of visual representation.
By generalizing inner product with a bilinear matrix, we propose the neural
similarity which serves as a learnable parametric similarity measure for CNNs.
Neural similarity naturally generalizes the convolution and enhances
flexibility. Further, we consider the neural similarity learning (NSL) in order
to learn the neural similarity adaptively from training data. Specifically, we
propose two different ways of learning the neural similarity: static NSL and
dynamic NSL. Interestingly, dynamic neural similarity makes the CNN become a
dynamic inference network. By regularizing the bilinear matrix, NSL can be
viewed as learning the shape of kernel and the similarity measure
simultaneously. We further justify the effectiveness of NSL with a theoretical
viewpoint. Most importantly, NSL shows promising performance in visual
recognition and few-shot learning, validating the superiority of NSL over the
inner product-based convolution counterparts.
In text/plain
format
Archived Files and Locations
application/pdf 772.9 kB
file_schgfg7y4vdivloeqzack4xkju
|
arxiv.org (repository) web.archive.org (webarchive) |
1910.13003v2
access all versions, variants, and formats of this works (eg, pre-prints)