Year: 2023
Type: preprint
Abstract: In this work, we introduce a novel deep learning architecture, Variable Length Embeddings (VLEs), an autoregressive model that can produce a latent representation composed of an arbitrary number of tokens. As a proof of concept, we demonstrate the capabilities of VLEs on tasks that involve reconstruction and image decomposition. We evaluate our experiments on a mix of the iNaturalist and ImageNet datasets and find that VLEs achieve comparable reconstruction results to a state of the art VAE, using less than a tenth of the parameters.
Source: arXiv (Cornell University)
Authors: Chiu, Johnathan, Gu, Andi, Zhou, Matt
Institutions: University of California, Berkeley, Harvard University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4377090784