Manifold Augmentation

Manifold augmentation is a data augmentation technique that generates synthetic training data by leveraging the underlying geometric structure (manifold) of the data distribution. Current research focuses on developing manifold augmentation methods tailored to various data types (tabular, image, text) and learning paradigms (self-supervised, supervised), often employing transformer-based models or generative models operating in feature embedding spaces. These techniques aim to improve model generalization, robustness to out-of-distribution data, and performance in low-data regimes, impacting fields ranging from computer vision and natural language processing to medical diagnosis and time-series analysis.

Papers

June 16, 2024

First-Order Manifold Data Augmentation for Regression Learning
Ilya Kaufman, Omri Azencot
Data Augmentation Distribution Generalization Domain Agnostic Domain Specific Augmentation Manifold Augmentation Regression via Classification

June 3, 2024

TabMDA: Tabular Manifold Data Augmentation for Any Classifier using Transformers with In-context Subsetting
Andrei Margeloiu, Adrián Bazaga, Nikola Simidjievski, Pietro Liò, Mateja Jamnik
Data Augmentation Transformer Megatron Decepticons Pre Trained Simple Classifier Different Context Tabular Datasets Manifold Augmentation

July 27, 2023

TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation
Moon Ye-Bin, Jisoo Kim, Hongyeob Kim, Kilho Son, Tae-Hyun Oh
Training Data Visual Representation Visual Feature Pre Trained Text Manifold Augmentation

June 23, 2023

Manifold Contrastive Learning with Variational Lie Group Operators
Kion Fallah, Alec Helbling, Kyle A. Johnsen, Christopher J. Rozell
Self Supervised Learning Representation Learning Lie Group Latent Manifold Manifold Augmentation

May 31, 2023

MSMix:An Interpolation-Based Text Data Augmentation Method Manifold Swap Mixup
Mao Ye, Haitao Wang, Zheqian Chen
Manifold Mixup Manifold Augmentation Interpolation Based Data Augmentation

February 28, 2023

Improving Model Generalization by On-manifold Adversarial Augmentation in the Frequency Domain
Chang Liu, Wenzhao Xiang, Yuan He, Hui Xue, Shibao Zheng, Hang Su
Adversarial Example Model Generalization Frequency Domain Adversarial Augmentation Manifold Augmentation Manifold Adversarial

December 14, 2022

Calibration-Free Driver Drowsiness Classification based on Manifold-Level Augmentation
Dong-Young Kim, Dong-Kyun Han, Hye-Bin Shin
Brain Dynamic Driver Drowsiness Detection Manifold Augmentation

November 5, 2022

Local Manifold Augmentation for Multiview Semantic Consistency
Yu Yang, Wing Yin Cheung, Chang Liu, Xiangyang Ji
Data Augmentation Supervised ImageNet View Consistency Manifold Augmentation

November 1, 2022

Augmentation Invariant Manifold Learning
Shulei Wang
Data Augmentation Self Supervised Representation Learning Invariant Manifold Manifold Augmentation

September 18, 2022

The Geometry of Self-supervised Learning Models and its Impact on Transfer Learning
Romain Cosentino, Sarath Shekkizhar, Mahdi Soltanolkotabi, Salman Avestimehr, Antonio Ortega
Transfer Learning Self Supervised Global Impact Geometric Analysis Geometric Control Product Manifold Manifold Augmentation