J Zhu, RM Moraes, S Karakulak, V Sobol… - arXiv preprint arXiv …, 2022 - arxiv.org
… to produce transformationinvariantrepresentations. To … transformationinvariance loss and covariance contrast loss, we get an encoder that is able to produce useful representations …
… a primer on visualrepresentations and … representation that is invariant to all transformations and selective for , there may be a dual representation that is invariant to all transformations …
BD Evans, SM Stringer - Frontiers in computational neuroscience, 2012 - frontiersin.org
… visual features. In previous computer simulation studies with rate-coded neural networks, the development of transformation-invariantrepresentations … and Continuous Transformation (…
J Liu, C Ju, W Xie, Y Zhang - Proceedings of the 30th ACM International …, 2022 - dl.acm.org
… We present a simple yet effective self-supervised framework for audio-visualrepresentation learning, to localize the sound source in videos. To understand what enables to learn useful …
A Mumuni, F Mumuni - SN Computer Science, 2021 - Springer
… a general overview of invariant feature representation in deep CNNs. A comprehensive discussion of state-of-the-art techniques for encoding geometric transformation in CNN models is …
P Cavanagh - Perception, 1978 - journals.sagepub.com
… An additional transformation of spatial frequency information is therefore demonstrated that … a size invariantrepresentation of form. The feasibility of the transform scheme in the visual …
… invariance to identitypreserving image transformations found along the ventral stream. Despite theoretical evidence that invariance … -preserving image transformations commonly used in …
… -invariant (rotation/reversal) image representation based on polar … In this way we can obtain identical representations for an … For handcrafted feature representation, we have proposed a …
K Sohn, H Lee - arXiv preprint arXiv:1206.6418, 2012 - arxiv.org
… framework of transformationinvariant feature learning by incorporating linear transformations into the feature learning algorithms. For example, we present the transformation-invariant re…