GridMix: Strong regularization through local context mapping

Baek, Kyungjune; Bang, Duhyeon; Shim, Hyunjung

doi:10.1016/j.patcog.2020.107594

Cited by 16 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method is considered a cutting technique due to its method of fusing two images. The cutting and replacement idea has also been used in FMix [8] and GridMix [16].…”

Section: Related Workmentioning

confidence: 99%

MiAMix: Enhancing Image Classification through a Multi-Stage Augmented Mixed Sample Data Augmentation Method

Liang,

Jia

2023

Processes

View full text Add to dashboard Cite

Despite substantial progress in the field of deep learning, overfitting persists as a critical challenge, and data augmentation has emerged as a particularly promising approach due to its capacity to enhance model generalization in various computer vision tasks. While various strategies have been proposed, Mixed Sample Data Augmentation (MSDA) has shown great potential for enhancing model performance and generalization. We introduce a novel mixup method called MiAMix, which stands for Multi-stage Augmented Mixup. MiAMix integrates image augmentation into the mixup framework, utilizes multiple diversified mixing methods concurrently, and improves the mixing method by randomly selecting mixing mask augmentation methods. Recent methods utilize saliency information and the MiAMix is designed for computational efficiency as well, reducing additional overhead and offering easy integration into existing training pipelines. We comprehensively evaluate MiAMix using four image benchmarks and pitting it against current state-of-the-art mixed sample data augmentation techniques to demonstrate that MiAMix improves performance without heavy computational overhead.

show abstract

“…This method is considered a cutting technique due to its method of fusing two images. The cutting and replacement idea has also been used in FMix [8] and GridMix [16].…”

Section: Related Workmentioning

confidence: 99%

MiAMix: Enhancing Image Classification through a Multi-Stage Augmented Mixed Sample Data Augmentation Method

Liang,

Jia

2023

Processes

View full text Add to dashboard Cite

show abstract

“…GridMix [45] 2021 Split two images into patches and spatially fuse the patches, linearly merge the annotation.…”

Section: Paper Year Highlightmentioning

confidence: 99%

“…To find the dominant regions faster, SuperMix [44] develops a variant of the newton iterative method. Like Hide and see [34] does, GridMix [45] divides images into grids and then each patch of the output image is randomly taken from the corresponding patches of two input images. Through the analysis, we believe that GridMask [51] can be adapted to mix two images.…”

Section: Continuousmentioning

confidence: 99%

A Comprehensive Survey of Image Augmentation Techniques for Deep Learning

Xu¹,

Yoon²,

Fuentes³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep learning has been achieving decent performance in computer vision requiring a large volume of images, however, collecting images is expensive and difficult in many scenarios. To alleviate this issue, many image augmentation algorithms have been proposed as effective and efficient strategies. Understanding current algorithms is essential to find suitable methods or develop novel techniques for given tasks. In this paper, we perform a comprehensive survey on image augmentation for deep learning with a novel informative taxonomy.To get the basic idea why we need image augmentation, we introduce the challenges in computer vision tasks and vicinity distribution. Then, the algorithms are split into three categories; model-free, model-based, and optimizing policybased. The model-free category employs image processing methods while the

show abstract

“…Such non-linear binary masking improves generalization [82,84] by increasing dataset: it creates new images with usually disjoint patches [33]. [4,20,52] seek more diverse transformations via arbitrarily shaped masks: proposals range from cow-spotted masks [24] to masks with irregular edges [33]. As masking of discriminative regions may cause label misallocation [30], [45,46,88,92] try to alleviate this issue with costly saliency heatmaps [76].…”

Section: Related Work 21 Data Augmentationmentioning

confidence: 99%

MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks

Ramé¹,

Sun

Cord

2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Recent strategies achieved ensembling "for free" by fitting concurrently diverse subnetworks inside a single base network. The main idea during training is that each subnetwork learns to classify only one of the multiple inputs simultaneously provided. However, the question of how to best mix these multiple inputs has not been studied so far.In this paper, we introduce MixMo, a new generalized framework for learning multi-input multi-output deep subnetworks. Our key motivation is to replace the suboptimal summing operation hidden in previous approaches by a more appropriate mixing mechanism. For that purpose, we draw inspiration from successful mixed sample data augmentations. We show that binary mixing in features -particularly with rectangular patches from CutMix -enhances results by making subnetworks stronger and more diverse.We improve state of the art for image classification on CIFAR-100 and Tiny ImageNet datasets. Our easy to implement models notably outperform data augmented deep ensembles, without the inference and memory overheads. As we operate in features and simply better leverage the expressiveness of large networks, we open a new line of research complementary to previous works.

show abstract

GridMix: Strong regularization through local context mapping

Cited by 16 publications

References 6 publications

MiAMix: Enhancing Image Classification through a Multi-Stage Augmented Mixed Sample Data Augmentation Method

MiAMix: Enhancing Image Classification through a Multi-Stage Augmented Mixed Sample Data Augmentation Method

A Comprehensive Survey of Image Augmentation Techniques for Deep Learning

MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks

Contact Info

Product

Resources

About