Remix: Rebalanced Mixup

• URL: http://arxiv.org/abs/2007.03943v3
• Date: Thu, 19 Nov 2020 13:33:21 GMT
• Title: Remix: Rebalanced Mixup
• Authors: Hsin-Ping Chou, Shih-Chieh Chang, Jia-Yu Pan, Wei Wei, Da-Cheng Juan
• Abstract summary: We propose a new regularization technique, Remix, that relaxes Mixup's formulation and enables the mixing factors of features and labels to be disentangled. We have studied the state-of-the art regularization techniques such as Mixup, Manifold Mixup and CutMix under class-imbalanced regime. We have also evaluated Remix on a real-world large-scale imbalanced dataset, iNaturalist 2018.
• Score: 25.733313524035232
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep image classifiers often perform poorly when training data are heavily class-imbalanced. In this work, we propose a new regularization technique, Remix, that relaxes Mixup's formulation and enables the mixing factors of features and labels to be disentangled. Specifically, when mixing two samples, while features are mixed in the same fashion as Mixup, Remix assigns the label in favor of the minority class by providing a disproportionately higher weight to the minority class. By doing so, the classifier learns to push the decision boundaries towards the majority classes and balance the generalization error between majority and minority classes. We have studied the state-of-the art regularization techniques such as Mixup, Manifold Mixup and CutMix under class-imbalanced regime, and shown that the proposed Remix significantly outperforms these state-of-the-arts and several re-weighting and re-sampling techniques, on the imbalanced datasets constructed by CIFAR-10, CIFAR-100, and CINIC-10. We have also evaluated Remix on a real-world large-scale imbalanced dataset, iNaturalist 2018. The experimental results confirmed that Remix provides consistent and significant improvements over the previous methods.

Related papers

• Who's the (Multi-)Fairest of Them \textsc{All}: Rethinking Interpolation-Based Data Augmentation Through the Lens of Multicalibration [1.0923877073891446]
  We stress-test four versions of Fair Mixup on two structured data classification problems with up to 81 marginalized groups. We find that on nearly every experiment, Fair Mixup textitworsens baseline performance and fairness, but the simple vanilla Mixup textitoutperforms both Fair Mixup and the baseline.
  arXiv  Detail & Related papers  (2024-12-13T21:36:12Z)
• Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognition [14.009773753739282]
  Long-tailed image recognition is a problem considering a real-world class distribution rather than an artificial uniform. In this paper, we tackle the problem from a different perspective to augment a training dataset to enhance the sample diversity of minority classes. Our method, namely Confusion-Pairing Mixup (CP-Mix), estimates the confusion distribution of the model and handles the data deficiency problem.
  arXiv  Detail & Related papers  (2024-11-12T08:08:31Z)
• PowMix: A Versatile Regularizer for Multimodal Sentiment Analysis [71.8946280170493]
  This paper introduces PowMix, a versatile embedding space regularizer that builds upon the strengths of unimodal mixing-based regularization approaches. PowMix is integrated before the fusion stage of multimodal architectures and facilitates intra-modal mixing, such as mixing text with text, to act as a regularizer.
  arXiv  Detail & Related papers  (2023-12-19T17:01:58Z)
• Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup [26.105340203096596]
  We show that non-random selection of pairs affects the training distribution and improve generalization by means completely unrelated to the mixing. We have found a new equivalence between two successful methods: selective mixup and resampling.
  arXiv  Detail & Related papers  (2023-05-26T10:56:22Z)
• Reweighted Mixup for Subpopulation Shift [63.1315456651771]
  Subpopulation shift exists in many real-world applications, which refers to the training and test distributions that contain the same subpopulation groups but with different subpopulation proportions. Importance reweighting is a classical and effective way to handle the subpopulation shift. We propose a simple yet practical framework, called reweighted mixup, to mitigate the overfitting issue.
  arXiv  Detail & Related papers  (2023-04-09T03:44:50Z)
• C-Mixup: Improving Generalization in Regression [71.10418219781575]
  Mixup algorithm improves generalization by linearly interpolating a pair of examples and their corresponding labels. We propose C-Mixup, which adjusts the sampling probability based on the similarity of the labels. C-Mixup achieves 6.56%, 4.76%, 5.82% improvements in in-distribution generalization, task generalization, and out-of-distribution robustness, respectively.
  arXiv  Detail & Related papers  (2022-10-11T20:39:38Z)
• RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness [94.69774317059122]
  We show that the effectiveness of the well celebrated Mixup can be further improved if instead of using it as the sole learning objective, it is utilized as an additional regularizer to the standard cross-entropy loss. This simple change not only provides much improved accuracy but also significantly improves the quality of the predictive uncertainty estimation of Mixup.
  arXiv  Detail & Related papers  (2022-06-29T09:44:33Z)
• Balanced-MixUp for Highly Imbalanced Medical Image Classification [19.338350044289736]
  We propose a novel mechanism for sampling training data based on the popular MixUp regularization technique. We experiment with a highly imbalanced dataset of retinal images and a long-tail dataset of gastro-intestinal video frames.
  arXiv  Detail & Related papers  (2021-09-20T21:31:31Z)
• PLM: Partial Label Masking for Imbalanced Multi-label Classification [59.68444804243782]
  Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. We propose a method, Partial Label Masking (PLM), which utilizes this ratio during training. Our method achieves strong performance when compared to existing methods on both multi-label (MultiMNIST and MSCOCO) and single-label (imbalanced CIFAR-10 and CIFAR-100) image classification datasets.
  arXiv  Detail & Related papers  (2021-05-22T18:07:56Z)
• An Empirical Study of the Effects of Sample-Mixing Methods for Efficient Training of Generative Adversarial Networks [0.0]
  It is well-known that training of generative adversarial networks (GANs) requires huge iterations before the generator's providing good-quality samples. We investigated the effect of sample mixing methods, that is, Mixup, CutMix, and SRMix, to alleviate this problem.
  arXiv  Detail & Related papers  (2021-04-08T06:40:23Z)
• M2m: Imbalanced Classification via Major-to-minor Translation [79.09018382489506]
  In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion. In this paper, we explore a novel yet simple way to alleviate this issue by augmenting less-frequent classes via translating samples from more-frequent classes. Our experimental results on a variety of class-imbalanced datasets show that the proposed method improves the generalization on minority classes significantly compared to other existing re-sampling or re-weighting methods.
  arXiv  Detail & Related papers  (2020-04-01T13:21:17Z)

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.