Control+Shift: Generating Controllable Distribution Shifts

• URL: http://arxiv.org/abs/2409.07940v1
• Date: Thu, 12 Sep 2024 11:07:53 GMT
• Title: Control+Shift: Generating Controllable Distribution Shifts
• Authors: Roy Friedman, Rhea Chowers,
• Abstract summary: We propose a new method for generating realistic datasets with distribution shifts using any decoder-based generative model. Our approach systematically creates datasets with varying intensities of distribution shifts, facilitating a comprehensive analysis of model performance degradation.
• Score: 1.3060023718506917
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a new method for generating realistic datasets with distribution shifts using any decoder-based generative model. Our approach systematically creates datasets with varying intensities of distribution shifts, facilitating a comprehensive analysis of model performance degradation. We then use these generated datasets to evaluate the performance of various commonly used networks and observe a consistent decline in performance with increasing shift intensity, even when the effect is almost perceptually unnoticeable to the human eye. We see this degradation even when using data augmentations. We also find that enlarging the training dataset beyond a certain point has no effect on the robustness and that stronger inductive biases increase robustness.

Related papers

• The Data Addition Dilemma [4.869513274920574]
  In many machine learning for healthcare tasks, standard datasets are constructed by amassing data across many, often fundamentally dissimilar, sources. But when does adding more data help, and when does it hinder progress on desired model outcomes in real-world settings? We identify this situation as the textitData Addition Dilemma, demonstrating that adding training data in this multi-source scaling context can at times result in reduced overall accuracy, uncertain fairness outcomes, and reduced worst-subgroup performance.
  arXiv  Detail & Related papers  (2024-08-08T01:42:31Z)
• 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)
• DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception [78.26734070960886]
  Current perceptive models heavily depend on resource-intensive datasets. We introduce perception-aware loss (P.A. loss) through segmentation, improving both quality and controllability. Our method customizes data augmentation by extracting and utilizing perception-aware attribute (P.A. Attr) during generation.
  arXiv  Detail & Related papers  (2024-03-20T04:58:03Z)
• Enhancing Visual Perception in Novel Environments via Incremental Data Augmentation Based on Style Transfer [2.516855334706386]
  "unknown unknowns" challenge autonomous agent deployment in real-world scenarios. Our approach enhances visual perception by leveraging the Variational Prototyping (VPE) to adeptly identify and handle novel inputs. Our findings suggest the potential benefits of incorporating generative models for domain-specific augmentation strategies.
  arXiv  Detail & Related papers  (2023-09-16T03:06:31Z)
• Leaving Reality to Imagination: Robust Classification via Generated Datasets [24.411444438920988]
  Recent research on robustness has revealed significant performance gaps between neural image classifiers trained on datasets similar to the test set. We study the question: How do generated datasets influence the natural robustness of image classifiers? We find that Imagenet classifiers trained on real data augmented with generated data achieve higher accuracy and effective robustness than standard training.
  arXiv  Detail & Related papers  (2023-02-05T22:49:33Z)
• Augmentation-induced Consistency Regularization for Classification [25.388324221293203]
  We propose a consistency regularization framework based on data augmentation, called CR-Aug. CR-Aug forces the output distributions of different sub models generated by data augmentation to be consistent with each other. We implement CR-Aug to image and audio classification tasks and conduct extensive experiments to verify its effectiveness.
  arXiv  Detail & Related papers  (2022-05-25T03:15:36Z)
• Generative Modeling Helps Weak Supervision (and Vice Versa) [87.62271390571837]
  We propose a model fusing weak supervision and generative adversarial networks. It captures discrete variables in the data alongside the weak supervision derived label estimate. It is the first approach to enable data augmentation through weakly supervised synthetic images and pseudolabels.
  arXiv  Detail & Related papers  (2022-03-22T20:24:21Z)
• Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations [76.82124752950148]
  We develop a convenient gradient-based method for selecting the data augmentation. We use a differentiable Kronecker-factored Laplace approximation to the marginal likelihood as our objective.
  arXiv  Detail & Related papers  (2022-02-22T02:51:11Z)
• Negative Data Augmentation [127.28042046152954]
  We show that negative data augmentation samples provide information on the support of the data distribution. We introduce a new GAN training objective where we use NDA as an additional source of synthetic data for the discriminator. Empirically, models trained with our method achieve improved conditional/unconditional image generation along with improved anomaly detection capabilities.
  arXiv  Detail & Related papers  (2021-02-09T20:28:35Z)
• 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.