CiTrus: Squeezing Extra Performance out of Low-data Bio-signal Transfer Learning

• URL: http://arxiv.org/abs/2412.11695v2
• Date: Wed, 18 Dec 2024 17:40:34 GMT
• Title: CiTrus: Squeezing Extra Performance out of Low-data Bio-signal Transfer Learning
• Authors: Eloy Geenjaar, Lie Lu,
• Abstract summary: Transfer learning for bio-signals has recently become an important technique to improve prediction performance on downstream tasks with small bio-signal datasets. We propose a new convolution-transformer hybrid model architecture with masked auto-encoding for low-data bio-signal transfer learning. Our findings indicate that the convolution-only part of our hybrid model can achieve state-of-the-art performance on some low-data downstream tasks.
• Score: 0.36832029288386137
• License:
• Abstract: Transfer learning for bio-signals has recently become an important technique to improve prediction performance on downstream tasks with small bio-signal datasets. Recent works have shown that pre-training a neural network model on a large dataset (e.g. EEG) with a self-supervised task, replacing the self-supervised head with a linear classification head, and fine-tuning the model on different downstream bio-signal datasets (e.g., EMG or ECG) can dramatically improve the performance on those datasets. In this paper, we propose a new convolution-transformer hybrid model architecture with masked auto-encoding for low-data bio-signal transfer learning, introduce a frequency-based masked auto-encoding task, employ a more comprehensive evaluation framework, and evaluate how much and when (multimodal) pre-training improves fine-tuning performance. We also introduce a dramatically more performant method of aligning a downstream dataset with a different temporal length and sampling rate to the original pre-training dataset. Our findings indicate that the convolution-only part of our hybrid model can achieve state-of-the-art performance on some low-data downstream tasks. The performance is often improved even further with our full model. In the case of transformer-based models we find that pre-training especially improves performance on downstream datasets, multimodal pre-training often increases those gains further, and our frequency-based pre-training performs the best on average for the lowest and highest data regimes.

Related papers

• Leveraging Semi-Supervised Learning to Enhance Data Mining for Image Classification under Limited Labeled Data [35.431340001608476]
  Traditional data mining methods are inadequate when faced with large-scale, high-dimensional and complex data. This study introduces semi-supervised learning methods, aiming to improve the algorithm's ability to utilize unlabeled data. Specifically, we adopt a self-training method and combine it with a convolutional neural network (CNN) for image feature extraction and classification.
  arXiv  Detail & Related papers  (2024-11-27T18:59:50Z)
• Multi-Scale Convolutional LSTM with Transfer Learning for Anomaly Detection in Cellular Networks [1.1432909951914676]
  This study introduces a novel approach Multi-Scale Convolutional LSTM with Transfer Learning (TL) to detect anomalies in cellular networks. The model is initially trained from scratch using a publicly available dataset to learn typical network behavior. We compare the performance of the model trained from scratch with that of the fine-tuned model using TL.
  arXiv  Detail & Related papers  (2024-09-30T17:51:54Z)
• Convolutional Monge Mapping Normalization for learning on sleep data [63.22081662149488]
  We propose a new method called Convolutional Monge Mapping Normalization (CMMN) CMMN consists in filtering the signals in order to adapt their power spectrum density (PSD) to a Wasserstein barycenter estimated on training data. Numerical experiments on sleep EEG data show that CMMN leads to significant and consistent performance gains independent from the neural network architecture.
  arXiv  Detail & Related papers  (2023-05-30T08:24:01Z)
• Convolutional Neural Networks for the classification of glitches in gravitational-wave data streams [52.77024349608834]
  We classify transient noise signals (i.e.glitches) and gravitational waves in data from the Advanced LIGO detectors. We use models with a supervised learning approach, both trained from scratch using the Gravity Spy dataset. We also explore a self-supervised approach, pre-training models with automatically generated pseudo-labels.
  arXiv  Detail & Related papers  (2023-03-24T11:12:37Z)
• Beyond Transfer Learning: Co-finetuning for Action Localisation [64.07196901012153]
  We propose co-finetuning -- simultaneously training a single model on multiple upstream'' and downstream'' tasks. We demonstrate that co-finetuning outperforms traditional transfer learning when using the same total amount of data. We also show how we can easily extend our approach to multiple upstream'' datasets to further improve performance.
  arXiv  Detail & Related papers  (2022-07-08T10:25:47Z)
• Transfer Learning Based Efficient Traffic Prediction with Limited Training Data [3.689539481706835]
  Efficient prediction of internet traffic is an essential part of Self Organizing Network (SON) for ensuring proactive management. Deep sequence model in network traffic prediction with limited training data has not been studied extensively in the current works. We investigated and evaluated the performance of the deep transfer learning technique in traffic prediction with inadequate historical data.
  arXiv  Detail & Related papers  (2022-05-09T14:44:39Z)
• Self-Supervised Pre-Training for Transformer-Based Person Re-Identification [54.55281692768765]
  Transformer-based supervised pre-training achieves great performance in person re-identification (ReID) Due to the domain gap between ImageNet and ReID datasets, it usually needs a larger pre-training dataset to boost the performance. This work aims to mitigate the gap between the pre-training and ReID datasets from the perspective of data and model structure.
  arXiv  Detail & Related papers  (2021-11-23T18:59:08Z)
• The Imaginative Generative Adversarial Network: Automatic Data Augmentation for Dynamic Skeleton-Based Hand Gesture and Human Action Recognition [27.795763107984286]
  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.
  arXiv  Detail & Related papers  (2021-05-27T11:07:09Z)
• Adaptive Weighting Scheme for Automatic Time-Series Data Augmentation [79.47771259100674]
  We present two sample-adaptive automatic weighting schemes for data augmentation. We validate our proposed methods on a large, noisy financial dataset and on time-series datasets from the UCR archive. On the financial dataset, we show that the methods in combination with a trading strategy lead to improvements in annualized returns of over 50$%$, and on the time-series data we outperform state-of-the-art models on over half of the datasets, and achieve similar performance in accuracy on the others.
  arXiv  Detail & Related papers  (2021-02-16T17:50:51Z)
• 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.