The Imaginative Generative Adversarial Network: Automatic Data
Augmentation for Dynamic Skeleton-Based Hand Gesture and Human Action
Recognition
- URL: http://arxiv.org/abs/2105.13061v2
- Date: Thu, 10 Aug 2023 18:54:19 GMT
- Title: The Imaginative Generative Adversarial Network: Automatic Data
Augmentation for Dynamic Skeleton-Based Hand Gesture and Human Action
Recognition
- Authors: Junxiao Shen and John Dudley and Per Ola Kristensson
- Abstract summary: We present a novel automatic data augmentation model, which approximates the distribution of the input data and samples new data from this distribution.
Our results show that the augmentation strategy is fast to train and can improve classification accuracy for both neural networks and state-of-the-art methods.
- Score: 27.795763107984286
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep learning approaches deliver state-of-the-art performance in recognition
of spatiotemporal human motion data. However, one of the main challenges in
these recognition tasks is limited available training data. Insufficient
training data results in over-fitting and data augmentation is one approach to
address this challenge. Existing data augmentation strategies based on scaling,
shifting and interpolating offer limited generalizability and typically require
detailed inspection of the dataset as well as hundreds of GPU hours for
hyperparameter optimization. In this paper, we present a novel automatic data
augmentation model, the Imaginative Generative Adversarial Network (GAN), that
approximates the distribution of the input data and samples new data from this
distribution. It is automatic in that it requires no data inspection and little
hyperparameter tuning and therefore it is a low-cost and low-effort approach to
generate synthetic data. We demonstrate our approach on small-scale
skeleton-based datasets with a comprehensive experimental analysis. Our results
show that the augmentation strategy is fast to train and can improve
classification accuracy for both conventional neural networks and
state-of-the-art methods.
Related papers
- DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data [61.62554324594797]
We propose DreamMask, which explores how to generate training data in the open-vocabulary setting, and how to train the model with both real and synthetic data.
In general, DreamMask significantly simplifies the collection of large-scale training data, serving as a plug-and-play enhancement for existing methods.
For instance, when trained on COCO and tested on ADE20K, the model equipped with DreamMask outperforms the previous state-of-the-art by a substantial margin of 2.1% mIoU.
arXiv Detail & Related papers (2025-01-03T19:00:00Z) - Enhancing Activity Recognition After Stroke: Generative Adversarial Networks for Kinematic Data Augmentation [0.0]
Generalizability of machine learning models for wearable monitoring in stroke rehabilitation is often constrained by the limited scale and heterogeneity of available data.
Data augmentation addresses this challenge by adding computationally derived data to real data to enrich the variability represented in the training set.
This study employs Conditional Generative Adversarial Networks (cGANs) to create synthetic kinematic data from a publicly available dataset.
By training deep learning models on both synthetic and experimental data, we enhanced task classification accuracy: models incorporating synthetic data attained an overall accuracy of 80.0%, significantly higher than the 66.1% seen in models trained solely with real data
arXiv Detail & Related papers (2024-06-12T15:51:00Z) - A survey of synthetic data augmentation methods in computer vision [0.0]
This paper presents an extensive review of synthetic data augmentation techniques.
We focus on the important data generation and augmentation techniques, general scope of application and specific use-cases.
We provide a summary of common synthetic datasets for training computer vision models.
arXiv Detail & Related papers (2024-03-15T07:34:08Z) - DaFoEs: Mixing Datasets towards the generalization of vision-state
deep-learning Force Estimation in Minimally Invasive Robotic Surgery [6.55111164866752]
We present a new vision-haptic dataset (DaFoEs) with variable soft environments for the training of deep neural models.
We also present a variable encoder-decoder architecture to predict the forces done by the laparoscopic tool using single input or sequence of inputs.
arXiv Detail & Related papers (2024-01-17T14:39:55Z) - ScoreMix: A Scalable Augmentation Strategy for Training GANs with
Limited Data [93.06336507035486]
Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available.
We present ScoreMix, a novel and scalable data augmentation approach for various image synthesis tasks.
arXiv Detail & Related papers (2022-10-27T02:55:15Z) - Convolutional generative adversarial imputation networks for
spatio-temporal missing data in storm surge simulations [86.5302150777089]
Generative Adversarial Imputation Nets (GANs) and GAN-based techniques have attracted attention as unsupervised machine learning methods.
We name our proposed method as Con Conval Generative Adversarial Imputation Nets (Conv-GAIN)
arXiv Detail & Related papers (2021-11-03T03:50:48Z) - A Data-Centric Approach for Training Deep Neural Networks with Less Data [1.9014535120129343]
This paper summarizes our winning submission to the "Data-Centric AI" competition.
We discuss some of the challenges that arise while training with a small dataset.
We propose a GAN-based solution for synthesizing new data points.
arXiv Detail & Related papers (2021-10-07T16:41:52Z) - Transformer Networks for Data Augmentation of Human Physical Activity
Recognition [61.303828551910634]
State of the art models like Recurrent Generative Adrial Networks (RGAN) are used to generate realistic synthetic data.
In this paper, transformer based generative adversarial networks which have global attention on data, are compared on PAMAP2 and Real World Human Activity Recognition data sets with RGAN.
arXiv Detail & Related papers (2021-09-02T16:47:29Z) - Improved Speech Emotion Recognition using Transfer Learning and
Spectrogram Augmentation [56.264157127549446]
Speech emotion recognition (SER) is a challenging task that plays a crucial role in natural human-computer interaction.
One of the main challenges in SER is data scarcity.
We propose a transfer learning strategy combined with spectrogram augmentation.
arXiv Detail & Related papers (2021-08-05T10:39:39Z) - Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training.
We experimentally verify that the new dataset can significantly improve the ability of the learned FER model.
To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
arXiv Detail & Related papers (2020-05-18T09:36:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.