EnsAug: Augmentation-Driven Ensembles for Human Motion Sequence Analysis
🤖 AI Summary
This work addresses the limitations of existing data augmentation methods in human motion modeling, which often disregard geometric and kinematic constraints, leading to unrealistic synthesized actions, and struggle to effectively integrate diverse augmentation signals within a single model. To overcome these issues, the authors propose EnsAug, an augmentation-driven ensemble-of-experts framework that trains dedicated models for each geometric augmentation strategy, departing from the conventional paradigm of training a single model with mixed augmentations. EnsAug is the first to systematically leverage individual augmentation strategies to construct a modular expert ensemble, thereby enhancing diversity while preserving kinematic plausibility. Evaluated on sign language recognition and human activity recognition benchmarks, EnsAug achieves state-of-the-art performance, significantly outperforming existing approaches, and demonstrates superior efficiency and modularity.
Application Category
📝 Abstract
Data augmentation is a crucial technique for training robust deep learning models for human motion, where annotated datasets are often scarce. However, generic augmentation methods often ignore the underlying geometric and kinematic constraints of the human body, risking the generation of unrealistic motion patterns that can degrade model performance. Furthermore, the conventional approach of training a single generalist model on a dataset expanded with a mixture of all available transformations does not fully exploit the unique learning signals provided by each distinct augmentation type. We challenge this convention by introducing a novel training paradigm, EnsAug, that strategically uses augmentation to foster model diversity within an ensemble. Our method involves training an ensemble of specialists, where each model learns from the original dataset augmented by only a single, distinct geometric transformation. Experiments on sign language and human activity recognition benchmarks demonstrate that our diversified ensemble methodology significantly outperforms the standard practice of training one model on a combined augmented dataset and achieves state-of-the-art accuracy on two sign language and one human activity recognition dataset while offering greater modularity and efficiency. Our primary contribution is the empirical validation of this training strategy, establishing an effective baseline for leveraging data augmentation in skeletal motion analysis.
Problem
Research questions and friction points this paper is trying to address.
data augmentation
human motion analysis
geometric constraints
kinematic constraints
ensemble learning
Innovation
Methods, ideas, or system contributions that make the work stand out.
EnsAug
augmentation-driven ensemble
human motion analysis
geometric transformation
specialist models
🔎 Similar Papers
No similar papers found.
