SeqAug: Sequential Feature Resampling as a modality agnostic augmentation method

2023/05/03 by Efthymios Georgiou, Georgiou, Efthymios, Alexandros Potamianos +1 · 1 citation
Computer Science · #Advanced Neural Network Applications #Anomaly Detection Techniques and Applications #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification

paper · pdf · doi:10.48550/arxiv.2305.01954

openalex publication_date 2023/05/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Enhancing Speech Emotion Recognition with Graph-Based Multimodal Fusion and Prosodic Features for the Speech Emotion Recognition in Naturalistic Conditions Challenge at Interspeech 2025

Related

• Modality Prompts for Arbitrary Modality Salient Object Detection
• DiMPLe -- Disentangled Multi-Modal Prompt Learning: Enhancing Out-Of-Distribution Alignment with Invariant and Spurious Feature Separation
• FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning
• MetAug: Contrastive Learning via Meta Feature Augmentation
• Good-Enough Compositional Data Augmentation