TorMentor: Deterministic dynamic-path, data augmentations with fractals

• URL: http://arxiv.org/abs/2204.03776v1
• Date: Thu, 7 Apr 2022 23:28:12 GMT
• Title: TorMentor: Deterministic dynamic-path, data augmentations with fractals
• Authors: Anguelos Nicolaou, Vincent Christlein, Edgar Riba, Jian Shi, Georg Vogeler, Mathias Seuret
• Abstract summary: We employ plasma fractals for adapting global image augmentation transformations into continuous local transforms. We present the TorMentor image augmentation framework that is totally modular and deterministic across images and point-clouds.
• Score: 8.100004428378066
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose the use of fractals as a means of efficient data augmentation. Specifically, we employ plasma fractals for adapting global image augmentation transformations into continuous local transforms. We formulate the diamond square algorithm as a cascade of simple convolution operations allowing efficient computation of plasma fractals on the GPU. We present the TorMentor image augmentation framework that is totally modular and deterministic across images and point-clouds. All image augmentation operations can be combined through pipelining and random branching to form flow networks of arbitrary width and depth. We demonstrate the efficiency of the proposed approach with experiments on document image segmentation (binarization) with the DIBCO datasets. The proposed approach demonstrates superior performance to traditional image augmentation techniques. Finally, we use extended synthetic binary text images in a self-supervision regiment and outperform the same model when trained with limited data and simple extensions.

Related papers

• MGAug: Multimodal Geometric Augmentation in Latent Spaces of Image Deformations [2.711740183729759]
  We propose a novel model that generates augmenting transformations in a multimodal latent space of geometric deformations. Experimental results show that our proposed approach outperforms all baselines by significantly improved prediction accuracy.
  arXiv  Detail & Related papers  (2023-12-20T21:30:55Z)
• Masked Autoencoders are Robust Data Augmentors [90.34825840657774]
  Regularization techniques like image augmentation are necessary for deep neural networks to generalize well. We propose a novel perspective of augmentation to regularize the training process. We show that utilizing such model-based nonlinear transformation as data augmentation can improve high-level recognition tasks.
  arXiv  Detail & Related papers  (2022-06-10T02:41:48Z)
• Feature transforms for image data augmentation [74.12025519234153]
  In image classification, many augmentation approaches utilize simple image manipulation algorithms. In this work, we build ensembles on the data level by adding images generated by combining fourteen augmentation approaches. Pretrained ResNet50 networks are finetuned on training sets that include images derived from each augmentation method.
  arXiv  Detail & Related papers  (2022-01-24T14:12:29Z)
• CSformer: Bridging Convolution and Transformer for Compressive Sensing [65.22377493627687]
  This paper proposes a hybrid framework that integrates the advantages of leveraging detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing.
  arXiv  Detail & Related papers  (2021-12-31T04:37:11Z)
• Learning Discriminative Shrinkage Deep Networks for Image Deconvolution [122.79108159874426]
  We propose an effective non-blind deconvolution approach by learning discriminative shrinkage functions to implicitly model these terms. Experimental results show that the proposed method performs favorably against the state-of-the-art ones in terms of efficiency and accuracy.
  arXiv  Detail & Related papers  (2021-11-27T12:12:57Z)
• Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation [17.539828821476224]
  We propose an adversarial data augmentation approach to improve the efficiency in utilizing training data. We present a generic task-driven learning framework, which jointly optimize a data augmentation model and a segmentation network during training. The proposed adversarial data augmentation does not rely on generative networks and can be used as a plug-in module in general segmentation networks.
  arXiv  Detail & Related papers  (2021-08-07T11:32:37Z)
• Scalable Visual Transformers with Hierarchical Pooling [61.05787583247392]
  We propose a Hierarchical Visual Transformer (HVT) which progressively pools visual tokens to shrink the sequence length. It brings a great benefit by scaling dimensions of depth/width/resolution/patch size without introducing extra computational complexity. Our HVT outperforms the competitive baselines on ImageNet and CIFAR-100 datasets.
  arXiv  Detail & Related papers  (2021-03-19T03:55:58Z)
• RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse prior [2.274915755738124]
  Flow-based generative models have become an important class of unsupervised learning approaches. In this work, we incorporate the key ideas of renormalization group (RG) and sparse prior distribution to design a hierarchical flow-based generative model, RG-Flow. Our proposed method has $O(log L)$ complexity for inpainting of an image with edge length $L$, compared to previous generative models with $O(L2)$ complexity.
  arXiv  Detail & Related papers  (2020-09-30T18:04:04Z)
• FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning [64.32306537419498]
  We propose a novel learned feature-based refinement and augmentation method that produces a varied set of complex transformations. These transformations also use information from both within-class and across-class representations that we extract through clustering. We demonstrate that our method is comparable to current state of art for smaller datasets while being able to scale up to larger datasets.
  arXiv  Detail & Related papers  (2020-07-16T17:55:31Z)
• On Box-Cox Transformation for Image Normality and Pattern Classification [0.6548580592686074]
  This paper revolves around the utility of such a tool as a pre-processing step to transform two-dimensional data. We compare the effect of this light-weight Box-Cox transformation with well-established state-of-the-art low light image enhancement techniques. We also demonstrate the effectiveness of our approach through several test-bed data sets for generic improvement of visual appearance of images.
  arXiv  Detail & Related papers  (2020-04-15T17:10:18Z)

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.