Augmentation Learning for Semi-Supervised Classification
- URL: http://arxiv.org/abs/2208.01956v1
- Date: Wed, 3 Aug 2022 10:06:51 GMT
- Title: Augmentation Learning for Semi-Supervised Classification
- Authors: Tim Frommknecht, Pedro Alves Zipf, Quanfu Fan, Nina Shvetsova, and
Hilde Kuehne
- Abstract summary: We propose a Semi-Supervised Learning method that automatically selects the most effective data augmentation policy for a particular dataset.
We show how policy learning can be used to adapt augmentations to datasets beyond ImageNet.
- Score: 13.519613713213277
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, a number of new Semi-Supervised Learning methods have emerged. As
the accuracy for ImageNet and similar datasets increased over time, the
performance on tasks beyond the classification of natural images is yet to be
explored. Most Semi-Supervised Learning methods rely on a carefully manually
designed data augmentation pipeline that is not transferable for learning on
images of other domains. In this work, we propose a Semi-Supervised Learning
method that automatically selects the most effective data augmentation policy
for a particular dataset. We build upon the Fixmatch method and extend it with
meta-learning of augmentations. The augmentation is learned in additional
training before the classification training and makes use of bi-level
optimization, to optimize the augmentation policy and maximize accuracy. We
evaluate our approach on two domain-specific datasets, containing satellite
images and hand-drawn sketches, and obtain state-of-the-art results. We further
investigate in an ablation the different parameters relevant for learning
augmentation policies and show how policy learning can be used to adapt
augmentations to datasets beyond ImageNet.
Related papers
- When to Learn What: Model-Adaptive Data Augmentation Curriculum [32.99634881669643]
We propose Model Adaptive Data Augmentation (MADAug) to jointly train an augmentation policy network to teach the model when to learn what.
Unlike previous work, MADAug selects augmentation operators for each input image by a model-adaptive policy varying between training stages, producing a data augmentation curriculum optimized for better generalization.
arXiv Detail & Related papers (2023-09-09T10:35:27Z) - Local Magnification for Data and Feature Augmentation [53.04028225837681]
We propose an easy-to-implement and model-free data augmentation method called Local Magnification (LOMA)
LOMA generates additional training data by randomly magnifying a local area of the image.
Experiments show that our proposed LOMA, though straightforward, can be combined with standard data augmentation to significantly improve the performance on image classification and object detection.
arXiv Detail & Related papers (2022-11-15T02:51:59Z) - TeachAugment: Data Augmentation Optimization Using Teacher Knowledge [11.696069523681178]
We propose a data augmentation optimization method based on the adversarial strategy called TeachAugment.
We show that TeachAugment outperforms existing methods in experiments of image classification, semantic segmentation, and unsupervised representation learning tasks.
arXiv Detail & Related papers (2022-02-25T06:22:51Z) - Weakly Supervised Change Detection Using Guided Anisotropic Difusion [97.43170678509478]
We propose original ideas that help us to leverage such datasets in the context of change detection.
First, we propose the guided anisotropic diffusion (GAD) algorithm, which improves semantic segmentation results.
We then show its potential in two weakly-supervised learning strategies tailored for change detection.
arXiv Detail & Related papers (2021-12-31T10:03:47Z) - Smart(Sampling)Augment: Optimal and Efficient Data Augmentation for
Semantic Segmentation [68.8204255655161]
We provide the first study on semantic image segmentation and introduce two new approaches: textitSmartAugment and textitSmartSamplingAugment.
SmartAugment uses Bayesian Optimization to search over a rich space of augmentation strategies and achieves a new state-of-the-art performance in all semantic segmentation tasks we consider.
SmartSamplingAugment, a simple parameter-free approach with a fixed augmentation strategy competes in performance with the existing resource-intensive approaches and outperforms cheap state-of-the-art data augmentation methods.
arXiv Detail & Related papers (2021-10-31T13:04:45Z) - Learning Representational Invariances for Data-Efficient Action
Recognition [52.23716087656834]
We show that our data augmentation strategy leads to promising performance on the Kinetics-100, UCF-101, and HMDB-51 datasets.
We also validate our data augmentation strategy in the fully supervised setting and demonstrate improved performance.
arXiv Detail & Related papers (2021-03-30T17:59:49Z) - Adaptive Weighting Scheme for Automatic Time-Series Data Augmentation [79.47771259100674]
We present two sample-adaptive automatic weighting schemes for data augmentation.
We validate our proposed methods on a large, noisy financial dataset and on time-series datasets from the UCR archive.
On the financial dataset, we show that the methods in combination with a trading strategy lead to improvements in annualized returns of over 50$%$, and on the time-series data we outperform state-of-the-art models on over half of the datasets, and achieve similar performance in accuracy on the others.
arXiv Detail & Related papers (2021-02-16T17:50:51Z) - Spatio-temporal Data Augmentation for Visual Surveillance [0.0]
We propose a data augmentation technique suitable for visual surveillance for additional performance improvement.
Two data augmentation methods of adjusting background model images and past images are proposed.
It is shown that performance can be improved in difficult areas such as static and ghost objects, compared to previous studies.
arXiv Detail & Related papers (2021-01-25T04:55:10Z) - Data Augmentation for Meta-Learning [58.47185740820304]
meta-learning algorithms sample data, query data, and tasks on each training step.
Data augmentation can be used not only to expand the number of images available per class, but also to generate entirely new classes/tasks.
Our proposed meta-specific data augmentation significantly improves the performance of meta-learners on few-shot classification benchmarks.
arXiv Detail & Related papers (2020-10-14T13:48:22Z) - Learning Test-time Augmentation for Content-based Image Retrieval [42.188013259368766]
Off-the-shelf convolutional neural network features achieve outstanding results in many image retrieval tasks.
Existing image retrieval approaches require fine-tuning or modification of pre-trained networks to adapt to variations unique to the target data.
Our method enhances the invariance of off-the-shelf features by aggregating features extracted from images augmented at test-time, with augmentations guided by a policy learned through reinforcement learning.
arXiv Detail & Related papers (2020-02-05T05:08:41Z)
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.