Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing

• URL: http://arxiv.org/abs/2112.08796v1
• Date: Thu, 16 Dec 2021 11:27:48 GMT
• Title: Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing
• Authors: Joonhyung Park, June Yong Yang, Jinwoo Shin, Sung Ju Hwang, Eunho Yang
• Abstract summary: Mixup scheme suggests mixing a pair of samples to create an augmented training sample. We present a novel, yet simple Mixup-variant that captures the best of both worlds.
• Score: 104.630875328668
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Mixup scheme suggests mixing a pair of samples to create an augmented training sample and has gained considerable attention recently for improving the generalizability of neural networks. A straightforward and widely used extension of Mixup is to combine with regional dropout-like methods: removing random patches from a sample and replacing it with the features from another sample. Albeit their simplicity and effectiveness, these methods are prone to create harmful samples due to their randomness. To address this issue, 'maximum saliency' strategies were recently proposed: they select only the most informative features to prevent such a phenomenon. However, they now suffer from lack of sample diversification as they always deterministically select regions with maximum saliency, injecting bias into the augmented data. In this paper, we present, a novel, yet simple Mixup-variant that captures the best of both worlds. Our idea is two-fold. By stochastically sampling the features and 'grafting' them onto another sample, our method effectively generates diverse yet meaningful samples. Its second ingredient is to produce the label of the grafted sample by mixing the labels in a saliency-calibrated fashion, which rectifies supervision misguidance introduced by the random sampling procedure. Our experiments under CIFAR, Tiny-ImageNet, and ImageNet datasets show that our scheme outperforms the current state-of-the-art augmentation strategies not only in terms of classification accuracy, but is also superior in coping under stress conditions such as data corruption and object occlusion.

Related papers

• ProxiMix: Enhancing Fairness with Proximity Samples in Subgroups [17.672299431705262]
  Using linear mixup alone, a data augmentation technique, for bias mitigation, can still retain biases in dataset labels. We propose a novel pre-processing strategy in which both an existing mixup method and our new bias mitigation algorithm can be utilized. ProxiMix keeps both pairwise and proximity relationships for fairer data augmentation.
  arXiv  Detail & Related papers  (2024-10-02T00:47:03Z)
• Which Pretrain Samples to Rehearse when Finetuning Pretrained Models? [60.59376487151964]
  Fine-tuning pretrained models on specific tasks is now the de facto approach for text and vision tasks. A known pitfall of this approach is the forgetting of pretraining knowledge that happens during finetuning. We propose a novel sampling scheme, mix-cd, that identifies and prioritizes samples that actually face forgetting.
  arXiv  Detail & Related papers  (2024-02-12T22:32:12Z)
• BSGAN: A Novel Oversampling Technique for Imbalanced Pattern Recognitions [0.0]
  Class imbalanced problems (CIP) are one of the potential challenges in developing unbiased Machine Learning (ML) models for predictions. CIP occurs when data samples are not equally distributed between the two or multiple classes. We propose a hybrid oversampling technique by combining the power of borderline SMOTE and Generative Adrial Network to generate more diverse data.
  arXiv  Detail & Related papers  (2023-05-16T20:02:39Z)
• Don't Play Favorites: Minority Guidance for Diffusion Models [59.75996752040651]
  We present a novel framework that can make the generation process of the diffusion models focus on the minority samples. We develop minority guidance, a sampling technique that can guide the generation process toward regions with desired likelihood levels.
  arXiv  Detail & Related papers  (2023-01-29T03:08:47Z)
• Selectively increasing the diversity of GAN-generated samples [8.980453507536017]
  We propose a novel method to selectively increase the diversity of GAN-generated samples. We show the superiority of our method in a synthetic benchmark as well as a real-life scenario simulating data from the Zero Degree Calorimeter of ALICE experiment in CERN.
  arXiv  Detail & Related papers  (2022-07-04T16:27:06Z)
• Fake It Till You Make It: Near-Distribution Novelty Detection by Score-Based Generative Models [54.182955830194445]
  existing models either fail or face a dramatic drop under the so-called near-distribution" setting. We propose to exploit a score-based generative model to produce synthetic near-distribution anomalous data. Our method improves the near-distribution novelty detection by 6% and passes the state-of-the-art by 1% to 5% across nine novelty detection benchmarks.
  arXiv  Detail & Related papers  (2022-05-28T02:02:53Z)
• 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)
• 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)
• 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)

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.