SeqAug: Sequential Feature Resampling as a modality agnostic augmentation method
This addresses the need for flexible augmentation in sequence-based machine learning, though it appears incremental as it builds on existing resampling ideas.
The authors tackled the problem of data augmentation for sequential features by proposing SeqAug, a modality-agnostic method that resamples features along the temporal axis, achieving comparable results to state-of-the-art on CMU-MOSEI.
Data augmentation is a prevalent technique for improving performance in various machine learning applications. We propose SeqAug, a modality-agnostic augmentation method that is tailored towards sequences of extracted features. The core idea of SeqAug is to augment the sequence by resampling from the underlying feature distribution. Resampling is performed by randomly selecting feature dimensions and permuting them along the temporal axis. Experiments on CMU-MOSEI verify that SeqAug is modality agnostic; it can be successfully applied to a single modality or multiple modalities. We further verify its compatibility with both recurrent and transformer architectures, and also demonstrate comparable to state-of-the-art results.