Robust Classification by Coupling Data Mollification with Label Smoothing
- URL: http://arxiv.org/abs/2406.01494v1
- Date: Mon, 3 Jun 2024 16:21:29 GMT
- Title: Robust Classification by Coupling Data Mollification with Label Smoothing
- Authors: Markus Heinonen, Ba-Hien Tran, Michael Kampffmeyer, Maurizio Filippone,
- Abstract summary: We propose a novel approach coupling data augmentation, in the form of image noising and blurring, with label smoothing to align predicted label confidences with image degradation.
We demonstrate improved robustness and uncertainty quantification on the corrupted image benchmarks of the CIFAR and TinyImageNet datasets.
- Score: 25.66357344079206
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Introducing training-time augmentations is a key technique to enhance generalization and prepare deep neural networks against test-time corruptions. Inspired by the success of generative diffusion models, we propose a novel approach coupling data augmentation, in the form of image noising and blurring, with label smoothing to align predicted label confidences with image degradation. The method is simple to implement, introduces negligible overheads, and can be combined with existing augmentations. We demonstrate improved robustness and uncertainty quantification on the corrupted image benchmarks of the CIFAR and TinyImageNet datasets.
Related papers
- DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models [18.44432223381586]
Recently, a number of image-mixing-based augmentation techniques have been introduced to improve the generalization of deep neural networks.
In these techniques, two or more randomly selected natural images are mixed together to generate an augmented image.
We propose DiffuseMix, a novel data augmentation technique that leverages a diffusion model to reshape training images.
arXiv Detail & Related papers (2024-04-05T05:31:02Z) - Active Generation for Image Classification [50.18107721267218]
We propose to address the efficiency of image generation by focusing on the specific needs and characteristics of the model.
With a central tenet of active learning, our method, named ActGen, takes a training-aware approach to image generation.
arXiv Detail & Related papers (2024-03-11T08:45:31Z) - Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural
Image Compression [62.888755394395716]
This study presents an enhanced neural compression method designed for optimal visual fidelity.
We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss.
Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression.
arXiv Detail & Related papers (2024-01-25T08:11:27Z) - Robustness-Guided Image Synthesis for Data-Free Quantization [15.91924736452861]
We propose Robustness-Guided Image Synthesis (RIS) to enrich the semantics of synthetic images and improve image diversity.
RIS is a simple but effective method to enrich the semantics of synthetic images and improve image diversity.
We achieve state-of-the-art performance for various settings on data-free quantization and can be extended to other data-free compression tasks.
arXiv Detail & Related papers (2023-10-05T16:39:14Z) - CONVERT:Contrastive Graph Clustering with Reliable Augmentation [110.46658439733106]
We propose a novel CONtrastiVe Graph ClustEring network with Reliable AugmenTation (CONVERT)
In our method, the data augmentations are processed by the proposed reversible perturb-recover network.
To further guarantee the reliability of semantics, a novel semantic loss is presented to constrain the network.
arXiv Detail & Related papers (2023-08-17T13:07:09Z) - Training on Thin Air: Improve Image Classification with Generated Data [28.96941414724037]
Diffusion Inversion is a simple yet effective method to generate diverse, high-quality training data for image classification.
Our approach captures the original data distribution and ensures data coverage by inverting images to the latent space of Stable Diffusion.
We identify three key components that allow our generated images to successfully supplant the original dataset.
arXiv Detail & Related papers (2023-05-24T16:33:02Z) - 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) - Fast Hybrid Image Retargeting [0.0]
We propose a method that quantifies and limits warping distortions with the use of content-aware cropping.
Our method outperforms recent approaches, while running in a fraction of their execution time.
arXiv Detail & Related papers (2022-03-25T11:46:06Z) - 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) - On Feature Normalization and Data Augmentation [55.115583969831]
Moment Exchange encourages the model to utilize the moment information also for recognition models.
We replace the moments of the learned features of one training image by those of another, and also interpolate the target labels.
As our approach is fast, operates entirely in feature space, and mixes different signals than prior methods, one can effectively combine it with existing augmentation approaches.
arXiv Detail & Related papers (2020-02-25T18:59:05Z)
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.