SapAugment: Learning A Sample Adaptive Policy for Data Augmentation
- URL: http://arxiv.org/abs/2011.01156v2
- Date: Mon, 15 Feb 2021 18:02:59 GMT
- Title: SapAugment: Learning A Sample Adaptive Policy for Data Augmentation
- Authors: Ting-Yao Hu, Ashish Shrivastava, Jen-Hao Rick Chang, Hema Koppula,
Stefan Braun, Kyuyeon Hwang, Ozlem Kalinli, Oncel Tuzel
- Abstract summary: We propose a novel method to learn a Sample-Adaptive Policy for Augmentation -- SapAugment.
We show substantial improvement, up to 21% relative reduction in word error rate on LibriSpeech dataset, over the state-of-the-art speech augmentation method.
- Score: 21.044266725115577
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Data augmentation methods usually apply the same augmentation (or a mix of
them) to all the training samples. For example, to perturb data with noise, the
noise is sampled from a Normal distribution with a fixed standard deviation,
for all samples. We hypothesize that a hard sample with high training loss
already provides strong training signal to update the model parameters and
should be perturbed with mild or no augmentation. Perturbing a hard sample with
a strong augmentation may also make it too hard to learn from. Furthermore, a
sample with low training loss should be perturbed by a stronger augmentation to
provide more robustness to a variety of conditions. To formalize these
intuitions, we propose a novel method to learn a Sample-Adaptive Policy for
Augmentation -- SapAugment. Our policy adapts the augmentation parameters based
on the training loss of the data samples. In the example of Gaussian noise, a
hard sample will be perturbed with a low variance noise and an easy sample with
a high variance noise. Furthermore, the proposed method combines multiple
augmentation methods into a methodical policy learning framework and obviates
hand-crafting augmentation parameters by trial-and-error. We apply our method
on an automatic speech recognition (ASR) task, and combine existing and novel
augmentations using the proposed framework. We show substantial improvement, up
to 21% relative reduction in word error rate on LibriSpeech dataset, over the
state-of-the-art speech augmentation method.
Related papers
- Inference Stage Denoising for Undersampled MRI Reconstruction [13.8086726938161]
Reconstruction of magnetic resonance imaging (MRI) data has been positively affected by deep learning.
A key challenge remains: to improve generalisation to distribution shifts between the training and testing data.
arXiv Detail & Related papers (2024-02-12T12:50:10Z) - Data Pruning via Moving-one-Sample-out [61.45441981346064]
We propose a novel data-pruning approach called moving-one-sample-out (MoSo)
MoSo aims to identify and remove the least informative samples from the training set.
Experimental results demonstrate that MoSo effectively mitigates severe performance degradation at high pruning ratios.
arXiv Detail & Related papers (2023-10-23T08:00:03Z) - Intra-class Adaptive Augmentation with Neighbor Correction for Deep
Metric Learning [99.14132861655223]
We propose a novel intra-class adaptive augmentation (IAA) framework for deep metric learning.
We reasonably estimate intra-class variations for every class and generate adaptive synthetic samples to support hard samples mining.
Our method significantly improves and outperforms the state-of-the-art methods on retrieval performances by 3%-6%.
arXiv Detail & Related papers (2022-11-29T14:52:38Z) - 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) - DiscrimLoss: A Universal Loss for Hard Samples and Incorrect Samples
Discrimination [28.599571524763785]
Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance.
To relieve this issue, curriculum learning is proposed to improve model performance and generalization by ordering training samples in a meaningful sequence.
arXiv Detail & Related papers (2022-08-21T13:38:55Z) - ReSmooth: Detecting and Utilizing OOD Samples when Training with Data
Augmentation [57.38418881020046]
Recent DA techniques always meet the need for diversity in augmented training samples.
An augmentation strategy that has a high diversity usually introduces out-of-distribution (OOD) augmented samples.
We propose ReSmooth, a framework that firstly detects OOD samples in augmented samples and then leverages them.
arXiv Detail & Related papers (2022-05-25T09:29:27Z) - Jo-SRC: A Contrastive Approach for Combating Noisy Labels [58.867237220886885]
We propose a noise-robust approach named Jo-SRC (Joint Sample Selection and Model Regularization based on Consistency)
Specifically, we train the network in a contrastive learning manner. Predictions from two different views of each sample are used to estimate its "likelihood" of being clean or out-of-distribution.
arXiv Detail & Related papers (2021-03-24T07:26:07Z) - Reweighting Augmented Samples by Minimizing the Maximal Expected Loss [51.2791895511333]
We construct the maximal expected loss which is the supremum over any reweighted loss on augmented samples.
Inspired by adversarial training, we minimize this maximal expected loss and obtain a simple and interpretable closed-form solution.
The proposed method can generally be applied on top of any data augmentation methods.
arXiv Detail & Related papers (2021-03-16T09:31:04Z) - Minority Class Oversampling for Tabular Data with Deep Generative Models [4.976007156860967]
We study the ability of deep generative models to provide realistic samples that improve performance on imbalanced classification tasks via oversampling.
Our experiments show that the way the method of sampling does not affect quality, but runtime varies widely.
We also observe that the improvements in terms of performance metric, while shown to be significant, often are minor in absolute terms.
arXiv Detail & Related papers (2020-05-07T21:35:57Z)
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.