KeepOriginalAugment: Single Image-based Better Information-Preserving Data Augmentation Approach

• URL: http://arxiv.org/abs/2405.06354v1
• Date: Fri, 10 May 2024 09:37:36 GMT
• Title: KeepOriginalAugment: Single Image-based Better Information-Preserving Data Augmentation Approach
• Authors: Teerath Kumar, Alessandra Mileo, Malika Bendechache,
• Abstract summary: Advanced image data augmentation techniques play a pivotal role in enhancing the training of models for diverse computer vision tasks. We introduce KeepOriginalAugment, a novel data augmentation approach. Striking a balance between data diversity and information preservation, KeepOriginalAugment enables models to leverage both diverse salient and non-salient regions.
• Score: 46.74201905814679
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Advanced image data augmentation techniques play a pivotal role in enhancing the training of models for diverse computer vision tasks. Notably, SalfMix and KeepAugment have emerged as popular strategies, showcasing their efficacy in boosting model performance. However, SalfMix reliance on duplicating salient features poses a risk of overfitting, potentially compromising the model's generalization capabilities. Conversely, KeepAugment, which selectively preserves salient regions and augments non-salient ones, introduces a domain shift that hinders the exchange of crucial contextual information, impeding overall model understanding. In response to these challenges, we introduce KeepOriginalAugment, a novel data augmentation approach. This method intelligently incorporates the most salient region within the non-salient area, allowing augmentation to be applied to either region. Striking a balance between data diversity and information preservation, KeepOriginalAugment enables models to leverage both diverse salient and non-salient regions, leading to enhanced performance. We explore three strategies for determining the placement of the salient region minimum, maximum, or random and investigate swapping perspective strategies to decide which part (salient or non-salient) undergoes augmentation. Our experimental evaluations, conducted on classification datasets such as CIFAR-10, CIFAR-100, and TinyImageNet, demonstrate the superior performance of KeepOriginalAugment compared to existing state-of-the-art techniques.

Related papers

• Where Do We Stand with Implicit Neural Representations? A Technical and Performance Survey [16.89460694470542]
  Implicit Neural Representations (INRs) have emerged as a paradigm in knowledge representation. INRs leverage multilayer perceptrons (MLPs) to model data as continuous implicit functions. This survey introduces a clear taxonomy that categorises them into four key areas: activation functions, position encoding, combined strategies, and network structure.
  arXiv  Detail & Related papers  (2024-11-06T06:14:24Z)
• Saliency-Based diversity and fairness Metric and FaceKeepOriginalAugment: A Novel Approach for Enhancing Fairness and Diversity [46.74201905814679]
  We introduce an extension of the KeepOriginalAugment method, termed FaceKeepOriginalAugment, which explores various debiasing aspects-geographical, gender, and stereotypical biases-in computer vision models. By maintaining a delicate balance between data diversity and information preservation, our approach empowers models to exploit both diverse salient and non-salient regions. We quantify dataset diversity across a range of datasets, including Flickr Faces HQ (FFHQ), WIKI, IMDB, Labelled Faces in the Wild (LFW), UTK Faces, and Diverse dataset.
  arXiv  Detail & Related papers  (2024-10-29T13:49:23Z)
• Assessing Open-world Forgetting in Generative Image Model Customization [17.219815694562993]
  customizing diffusion models with new classes often leads to unintended consequences that compromise their reliability. Our research presents the first comprehensive investigation into open-world forgetting in diffusion models. We propose a mitigation strategy based on functional regularization to preserve original capabilities while accommodating new concepts.
  arXiv  Detail & Related papers  (2024-10-18T03:58:29Z)
• Data Augmentation via Latent Diffusion for Saliency Prediction [67.88936624546076]
  Saliency prediction models are constrained by the limited diversity and quantity of labeled data. We propose a novel data augmentation method for deep saliency prediction that edits natural images while preserving the complexity and variability of real-world scenes.
  arXiv  Detail & Related papers  (2024-09-11T14:36:24Z)
• A Review of Image Retrieval Techniques: Data Augmentation and Adversarial Learning Approaches [0.0]
  This review focuses on the roles of data augmentation and adversarial learning techniques in enhancing retrieval performance. Data augmentation enhances the model's generalization ability and robustness by generating more diverse training samples, simulating real-world variations, and reducing overfitting. adversarial attacks and defenses introduce perturbations during training to improve the model's robustness against potential attacks.
  arXiv  Detail & Related papers  (2024-09-02T12:55:17Z)
• A Simple Background Augmentation Method for Object Detection with Diffusion Model [53.32935683257045]
  In computer vision, it is well-known that a lack of data diversity will impair model performance. We propose a simple yet effective data augmentation approach by leveraging advancements in generative models. Background augmentation, in particular, significantly improves the models' robustness and generalization capabilities.
  arXiv  Detail & Related papers  (2024-08-01T07:40:00Z)
• A Novel Cross-Perturbation for Single Domain Generalization [54.612933105967606]
  Single domain generalization aims to enhance the ability of the model to generalize to unknown domains when trained on a single source domain. The limited diversity in the training data hampers the learning of domain-invariant features, resulting in compromised generalization performance. We propose CPerb, a simple yet effective cross-perturbation method to enhance the diversity of the training data.
  arXiv  Detail & Related papers  (2023-08-02T03:16:12Z)
• The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization [64.61630743818024]
  We introduce four new real-world distribution shift datasets consisting of changes in image style, image blurriness, geographic location, camera operation, and more. We find that using larger models and artificial data augmentations can improve robustness on real-world distribution shifts, contrary to claims in prior work. We also introduce a new data augmentation method which advances the state-of-the-art and outperforms models pretrained with 1000 times more labeled data.
  arXiv  Detail & Related papers  (2020-06-29T17:59:10Z)

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.