SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization

• URL: http://arxiv.org/abs/2006.01791v2
• Date: Tue, 27 Jul 2021 13:02:06 GMT
• Title: SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization
• Authors: A. F. M. Shahab Uddin, Mst. Sirazam Monira, Wheemyung Shin, TaeChoong Chung and Sung-Ho Bae
• Abstract summary: We propose SaliencyMix to improve the generalization ability of deep learning models. SaliencyMix carefully selects a representative image patch with the help of a saliency map and mixes this indicative patch with the target image. SaliencyMix achieves the best known top-1 error of 21.26% and 20.09% for ResNet-50 and ResNet-101 architectures on ImageNet classification.
• Score: 9.126576583256506
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Advanced data augmentation strategies have widely been studied to improve the generalization ability of deep learning models. Regional dropout is one of the popular solutions that guides the model to focus on less discriminative parts by randomly removing image regions, resulting in improved regularization. However, such information removal is undesirable. On the other hand, recent strategies suggest to randomly cut and mix patches and their labels among training images, to enjoy the advantages of regional dropout without having any pointless pixel in the augmented images. We argue that such random selection strategies of the patches may not necessarily represent sufficient information about the corresponding object and thereby mixing the labels according to that uninformative patch enables the model to learn unexpected feature representation. Therefore, we propose SaliencyMix that carefully selects a representative image patch with the help of a saliency map and mixes this indicative patch with the target image, thus leading the model to learn more appropriate feature representation. SaliencyMix achieves the best known top-1 error of 21.26% and 20.09% for ResNet-50 and ResNet-101 architectures on ImageNet classification, respectively, and also improves the model robustness against adversarial perturbations. Furthermore, models that are trained with SaliencyMix help to improve the object detection performance. Source code is available at https://github.com/SaliencyMix/SaliencyMix.

Related papers

• Semantically Proportional Patchmix for Few-Shot Learning [16.24173112047382]
  Few-shot learning aims to classify unseen classes with only a limited number of labeled data. Recent works have demonstrated that training models with a simple transfer learning strategy can achieve competitive results in few-shot classification. We proposeSePPMix, in which patches are cut and pasted among training images and the ground truth labels are mixed proportionally to the semantic information of the patches.
  arXiv  Detail & Related papers  (2022-02-17T13:24:33Z)
• Evolving Image Compositions for Feature Representation Learning [22.22790506995431]
  We propose PatchMix, a data augmentation method that creates new samples by composing patches from pairs of images in a grid-like pattern. A ResNet-50 model trained on ImageNet using PatchMix exhibits superior transfer learning capabilities across a wide array of benchmarks.
  arXiv  Detail & Related papers  (2021-06-16T17:57:18Z)
• Survey: Image Mixing and Deleting for Data Augmentation [0.0]
  Image mixing and deleting is a sub-area within data augmentation. Model trained with this approach has shown to perform and generalize well. Due to its low compute cost and success in recent past, many techniques of image mixing and deleting are proposed.
  arXiv  Detail & Related papers  (2021-06-13T20:32:24Z)
• CutPaste: Self-Supervised Learning for Anomaly Detection and Localization [59.719925639875036]
  We propose a framework for building anomaly detectors using normal training data only. We first learn self-supervised deep representations and then build a generative one-class classifier on learned representations. Our empirical study on MVTec anomaly detection dataset demonstrates the proposed algorithm is general to be able to detect various types of real-world defects.
  arXiv  Detail & Related papers  (2021-04-08T19:04:55Z)
• Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network [92.01145655155374]
  We present an unsupervised image enhancement generative network (UEGAN) It learns the corresponding image-to-image mapping from a set of images with desired characteristics in an unsupervised manner. Results show that the proposed model effectively improves the aesthetic quality of images.
  arXiv  Detail & Related papers  (2020-12-30T03:22:46Z)
• ResizeMix: Mixing Data with Preserved Object Information and True Labels [57.00554495298033]
  We study the importance of the saliency information for mixing data, and find that the saliency information is not so necessary for promoting the augmentation performance. We propose a more effective but very easily implemented method, namely ResizeMix.
  arXiv  Detail & Related papers  (2020-12-21T03:43:13Z)
• Shape-Texture Debiased Neural Network Training [50.6178024087048]
  Convolutional Neural Networks are often biased towards either texture or shape, depending on the training dataset. We develop an algorithm for shape-texture debiased learning. Experiments show that our method successfully improves model performance on several image recognition benchmarks.
  arXiv  Detail & Related papers  (2020-10-12T19:16:12Z)
• Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification [58.20132466198622]
  We propose Attentive CutMix, a naturally enhanced augmentation strategy based on CutMix. In each training iteration, we choose the most descriptive regions based on the intermediate attention maps from a feature extractor. Our proposed method is simple yet effective, easy to implement and can boost the baseline significantly.
  arXiv  Detail & Related papers  (2020-03-29T15:01:05Z)
• Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning [108.999497144296]
  Recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. This work aims to involve the distance concept on label space in the unsupervised learning and let the model be aware of the soft degree of similarity between positive or negative pairs. Despite its conceptual simplicity, we show empirically that with the solution -- Unsupervised image mixtures (Un-Mix), we can learn subtler, more robust and generalized representations from the transformed input and corresponding new label space.
  arXiv  Detail & Related papers  (2020-03-11T17:59:04Z)
• Continual Local Replacement for Few-shot Learning [13.956960291580938]
  The goal of few-shot learning is to learn a model that can recognize novel classes based on one or few training data. It is challenging mainly due to two aspects: (1) it lacks good feature representation of novel classes; (2) a few of labeled data could not accurately represent the true data distribution. A novel continual local replacement strategy is proposed to address the data deficiency problem.
  arXiv  Detail & Related papers  (2020-01-23T04:26:21Z)

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.