AlignMixup: Improving Representations By Interpolating Aligned Features - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

AlignMixup: Improving Representations By Interpolating Aligned Features

Abstract

Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels. Many recent mixup methods focus on cutting and pasting two or more objects into one image, which is more about efficient processing than interpolation. However, how to best interpolate images is not well defined. In this sense, mixup has been connected to autoencoders, because often autoencoders "interpolate well", for instance generating an image that continuously deforms into another. In this work, we revisit mixup from the interpolation perspective and introduce AlignMix, where we geometrically align two images in the feature space. The correspondences allow us to interpolate between two sets of features, while keeping the locations of one set. Interestingly, this gives rise to a situation where mixup retains mostly the geometry or pose of one image and the texture of the other, connecting it to style transfer. More than that, we show that an autoencoder can still improve representation learning under mixup, without the classifier ever seeing decoded images. AlignMix outperforms state-of-the-art mixup methods on five different benchmarks.
Fichier principal
Vignette du fichier
AlignMix_CVPR22_cameraReady.pdf (3.88 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03620779 , version 1 (26-03-2022)

Licence

Identifiers

  • HAL Id : hal-03620779 , version 1

Cite

Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg, Yannis Avrithis. AlignMixup: Improving Representations By Interpolating Aligned Features. CVPR 2022- IEEE/CVF Proceedings on Computer Vision and Pattern Recognition, Jun 2022, New Orleans (Louisiana), United States. ⟨hal-03620779⟩
94 View
106 Download

Share

Gmail Mastodon Facebook X LinkedIn More