paper-with-me

Papers

AAVAE: Augmentation-Augmented Variational Autoencoders

2021-09-29 · William Alejandro Falcon, Ananya Harsh Jha, Teddy Koker, Kyunghyun Cho

Recent methods for self-supervised learning can be grouped into two paradigms: contrastive and non-contrastive approaches. Their success can largely be attributed to data augmentation pipelines which generate multiple views of a single input that preserve the underlying semantics. In this work, we introduce augmentation-augmented variational autoencoders (AAVAE), yet another alternative to self-supervised learning, based on autoencoding. We derive AAVAE starting from the conventional variational autoencoder (VAE), by replacing the KL divergence regularization, which is agnostic to the input domain, with data augmentations that explicitly encourage the internal representations to encode domain-specific invariances and equivariances. We empirically evaluate the proposed AAVAE on image classification, similar to how recent contrastive and non-contrastive learning algorithms have been evaluated. Our experiments confirm the effectiveness of data augmentation as a replacement for KL divergence regularization. The AAVAE outperforms the VAE by 30% on CIFAR-10, 40% on STL-10 and 45% on Imagenet. On CIFAR-10 and STL-10, the results for AAVAE are largely comparable to the state-of-the-art algorithms for self-supervised learning.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningData Augmentationimage-classificationImage ClassificationSelf-Supervised Learning

Similar Papers 제목 키워드 기반

AASAE: Augmentation-Augmented Stochastic Autoencoders

2021-07-26 · William Falcon, Ananya Harsh Jha, Teddy Koker, Kyunghyun Cho

Recent methods for self-supervised learning can be grouped into two paradigms: contrastive and non-contrastive approaches. Their success can largely be attributed to data augmentation pipelines which generate multiple vi…

Contrastive LearningData Augmentationimage-classificationImage Classification+1

Category-Learning with Context-Augmented Autoencoder

2020-10-10 · Denis Kuzminykh, Laida Kushnareva, Timofey Grigoryev, Alexander Zatolokin

Finding an interpretable non-redundant representation of real-world data is one of the key problems in Machine Learning. Biological neural networks are known to solve this problem quite well in unsupervised manner, yet u…

Data Augmentation

Data Augmentation with Variational Autoencoders and Manifold Sampling

2021-03-25 · Clément Chadebec, Stéphanie Allassonnière

We propose a new efficient way to sample from a Variational Autoencoder in the challenging low sample size setting. This method reveals particularly well suited to perform data augmentation in such a low data regime and …

Data Augmentation

Synthetic Data Augmentation for Medical Audio Classification: A Preliminary Evaluation

2026-02-03 · David McShannon, Anthony Mella, Nicholas Dietrich arxiv

Medical audio classification remains challenging due to low signal-to-noise ratios, subtle discriminative features, and substantial intra-class variability, often compounded by class imbalance and limited training data. …

Audio ClassificationData Augmentation

Improving SMOTE via Fusing Conditional VAE for Data-adaptive Noise Filtering

2024-05-30 · Sungchul Hong, SeungHwan An, Jong-June Jeon

Recent advances in a generative neural network model extend the development of data augmentation methods. However, the augmentation methods based on the modern generative models fail to achieve notable performance for cl…

ClassificationData Augmentationimbalanced classification