RandMSAugment: A Mixed-Sample Augmentation for Limited-Data Scenarios

• URL: http://arxiv.org/abs/2311.16508v1
• Date: Sat, 25 Nov 2023 18:07:20 GMT
• Title: RandMSAugment: A Mixed-Sample Augmentation for Limited-Data Scenarios
• Abstract summary: We introduce a novel augmentation technique called RandMSAugment that integrates complementary strengths of existing methods. RandMSAugment significantly outperforms the competition on CIFAR-100, STL-10, and Tiny-Imagenet.
• Score: 3.018656336329545
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The high costs of annotating large datasets suggests a need for effectively training CNNs with limited data, and data augmentation is a promising direction. We study foundational augmentation techniques, including Mixed Sample Data Augmentations (MSDAs) and a no-parameter variant of RandAugment termed Preset-RandAugment, in the fully supervised scenario. We observe that Preset-RandAugment excels in limited-data contexts while MSDAs are moderately effective. We show that low-level feature transforms play a pivotal role in this performance difference, postulate a new property of augmentations related to their data efficiency, and propose new ways to measure the diversity and realism of augmentations. Building on these insights, we introduce a novel augmentation technique called RandMSAugment that integrates complementary strengths of existing methods. RandMSAugment significantly outperforms the competition on CIFAR-100, STL-10, and Tiny-Imagenet. With very small training sets (4, 25, 100 samples/class), RandMSAugment achieves compelling performance gains between 4.1% and 6.75%. Even with more training data (500 samples/class) we improve performance by 1.03% to 2.47%. RandMSAugment does not require hyperparameter tuning, extra validation data, or cumbersome optimizations.

Related papers

• Filtering with Confidence: When Data Augmentation Meets Conformal Prediction [10.431187957711206]
  We propose a principled data filtering framework for synthetic data augmentation.<n>We show consistent performance improvements of up to 40% in F1 score over unaugmented baselines.
  arXiv  Detail & Related papers  (2025-09-25T19:42:02Z)
• Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward [54.708851958671794]
  We propose a Data-Efficient Policy Optimization pipeline that combines optimized strategies for both offline and online data selection.<n>In offline phase, we curate a high-quality subset of training samples based on diversity, influence, and appropriate difficulty.<n>During online RLVR training, we introduce a sample-level explorability metric to dynamically filter samples with low exploration potential.
  arXiv  Detail & Related papers  (2025-09-01T10:04:20Z)
• Do We Need All the Synthetic Data? Towards Targeted Synthetic Image Augmentation via Diffusion Models [12.472871440252105]
  We show that synthetically augmenting part of the data that is not learned early in training outperforms augmenting the entire dataset.<n>Our method boosts the performance by up to2.8% in a variety of scenarios.<n>It can also easily stack with existing weak and strong augmentation strategies to further boost the performance.
  arXiv  Detail & Related papers  (2025-05-27T07:27:03Z)
• TLDR: Traffic Light Detection using Fourier Domain Adaptation in Hostile WeatheR [4.792412997390758]
  This paper proposes a novel approach by merging two widely used datasets, LISA and S2TLD. FDA helps the model trained on this final dataset adapt to rainy and foggy weather conditions. Experimental results demonstrate that models trained on FDA-augmented images outperform those trained without FDA.
  arXiv  Detail & Related papers  (2024-11-12T16:15:25Z)
• Ali-AUG: Innovative Approaches to Labeled Data Augmentation using One-Step Diffusion Model [0.14999444543328289]
  Ali-AUG is a novel single-step diffusion model for efficient labeled data augmentation in industrial applications. Our method addresses the challenge of limited labeled data by generating synthetic, labeled images with precise feature insertion.
  arXiv  Detail & Related papers  (2024-10-24T12:12:46Z)
• Multi-scale Contrastive Adaptor Learning for Segmenting Anything in Underperformed Scenes [12.36950265154199]
  We introduce a novel Multi-scale Contrastive Adaptor learning method named MCA-SAM. MCA-SAM enhances adaptor performance through a meticulously designed contrastive learning framework at both token and sample levels. Empirical results demonstrate that MCA-SAM sets new benchmarks, outperforming existing methods in three challenging domains.
  arXiv  Detail & Related papers  (2024-08-12T06:23:10Z)
• DualAug: Exploiting Additional Heavy Augmentation with OOD Data Rejection [77.6648187359111]
  We propose a novel data augmentation method, named textbfDualAug, to keep the augmentation in distribution as much as possible at a reasonable time and computational cost. Experiments on supervised image classification benchmarks show that DualAug improve various automated data augmentation method.
  arXiv  Detail & Related papers  (2023-10-12T08:55:10Z)
• Scaling Data Generation in Vision-and-Language Navigation [116.95534559103788]
  We propose an effective paradigm for generating large-scale data for learning. We apply 1200+ photo-realistic environments from HM3D and Gibson datasets and synthesizes 4.9 million instruction trajectory pairs. Thanks to our large-scale dataset, the performance of an existing agent can be pushed up (+11% absolute with regard to previous SoTA) to a significantly new best of 80% single-run success rate on the R2R test split by simple imitation learning.
  arXiv  Detail & Related papers  (2023-07-28T16:03:28Z)
• Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
  We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
  arXiv  Detail & Related papers  (2023-05-01T20:04:46Z)
• Augmentation-Aware Self-Supervision for Data-Efficient GAN Training [68.81471633374393]
  Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. We propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data. We compare our method with state-of-the-art (SOTA) methods using the class-conditional BigGAN and unconditional StyleGAN2 architectures.
  arXiv  Detail & Related papers  (2022-05-31T10:35:55Z)
• Learning Representational Invariances for Data-Efficient Action Recognition [52.23716087656834]
  We show that our data augmentation strategy leads to promising performance on the Kinetics-100, UCF-101, and HMDB-51 datasets. We also validate our data augmentation strategy in the fully supervised setting and demonstrate improved performance.
  arXiv  Detail & Related papers  (2021-03-30T17:59:49Z)
• Simple is Better! Lightweight Data Augmentation for Low Resource Slot Filling and Intent Classification [3.2996723916635267]
  We show that lightweight augmentation, a set of augmentation methods involving word span and sentence level operations, alleviates data scarcity problems. Experiments on limited data settings show that lightweight augmentation yields significant performance improvement on slot filling. Lightweight augmentation is also beneficial when combined with pre-trained LM-based models, as it improves BERT-based joint intent and slot filling models.
  arXiv  Detail & Related papers  (2020-09-08T12:39:47Z)
• How Does Data Augmentation Affect Privacy in Machine Learning? [94.52721115660626]
  We propose new MI attacks to utilize the information of augmented data. We establish the optimal membership inference when the model is trained with augmented data.
  arXiv  Detail & Related papers  (2020-07-21T02:21:10Z)
• On the Generalization Effects of Linear Transformations in Data Augmentation [32.01435459892255]
  Data augmentation is a powerful technique to improve performance in applications such as image and text classification tasks. We study a family of linear transformations and study their effects on the ridge estimator in an over-parametrized linear regression setting. We propose an augmentation scheme that searches over the space of transformations by how uncertain the model is about the transformed data.
  arXiv  Detail & Related papers  (2020-05-02T04:10:21Z)

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.