Comparison of data augmentation techniques
Fall 2020
Takumi Okoshi
Data Scientist
Product may differ from images depicted.
As a Z by HP Data Science Global Ambassador, Takumi Okoshi's content is sponsored and he was provided with HP products.
Hello, I'm Takuoko, a Kaggle Grandmaster.
In this post, I would like to compare data augmentation techniques, for both image classification and testing. Data augmentation is a powerful technique in CV competition.
I have compared the techniques used for image classification, which is the most standard in CV competition.
As a Z by HP Data Science Global Ambassador, I have been provided with high-powered HP workstations.
#developmentenvironment
I am working on a CV competition with the aforementioned powerful systems. Compared to the time when I used V100, I now have systems that can run freely at any time and obtain higher speeds, so the number of experiments that I can run has increased greatly compared to before, and I can also run comparative tests of various papers.
Environments such as PyTorch and CUDA are pre-installed in the systems, so there was no need for me to build the environment.
# Comparison images of data augmentation techniques
I would like to compare two images of CIFAR-100 by mixing them. Some of the figures are cited from papers.
## Mixup
[paper with code](https://paperswithcode.com/paper/mixup-beyond-empirical-risk-minimization)
A technique of mixing two images with lam * img1 + (1 - lam) * img2.
## Manifold Mixup
[paper with code](https://paperswithcode.com/paper/manifold-mixup-better-representations-by)
Example of mixup in the middle layer.
## CutMix
[paper with code](https://paperswithcode.com/paper/cutmix-regularization-strategy-to-train)
A technique in which one image is cut out with a bbox of a certain size and pasted into the other image.
There are two methods: corresponding paste which pastes at the same position as the cut-out position, and random paste which pastes at random positions.
## PatchUp
[paper with code](https://paperswithcode.com/paper/patchup-a-regularization-technique-for)
A method of running CutMix in the middle layer.
## ResizeMix
[paper with code](https://paperswithcode.com/paper/resizemix-mixing-data-with-preserved-object)
A technique in which one image is resized and pasted into the other.
## fmix
[paper with code](https://paperswithcode.com/paper/understanding-and-enhancing-mixed-sample-data)
Compared to CutMix, a mask can be generated and mixed regardless of the shape (does not have to be square).
## SnapMix
[paper with code](https://paperswithcode.com/paper/snapmix-semantically-proportional-mixing-for)
Reduce background image noise by using CAM to weight the label after mixing. Figure is cited from the paper.
## PuzzleMix
[paper with code](https://paperswithcode.com/paper/puzzle-mix-exploiting-saliency-and-local-1)
Reduces background noise by overlapping important parts. Figure is cited from the paper.
# Comparative testing of data augmentation techniques
Test Settings
Dataset:Kaggle’s [Cassava Leaf Disease Classification](https://www.kaggle.com/c/cassava-leaf-disease-classification)
Model:resnet34d
Loss:CrossEntropyLoss
Optimizer:Adam+Lookahead
Image Size:256
Batch Size:64
Epochs:20
Results
Technic: 5fold CV
CutMix random paste: 0.8708
CutMix corresponding paste: 0.8694
PatchUp: 0.8694
ManifoldMixup: 0.8692
ResizeMix: 0.8686
Cutmix corresponding paste + Mixup: 0.868
Fmix: 0.8675
PuzzleMix: 0.8662
Mixup: 0.8661
Summary
As noted in ResizeMix's paper, random paste was more accurate for CutMix. ResizeMix, on the other hand, was less accurate than CutMix, which is a different result from the paper.
Fmix's paper also mentioned that CutMix + Mixup and Fmix + Mixup were more accurate than either method alone, but this could not be replicated.
As for the methods, I felt that random paste and ResizeMix needed careful consideration to be applied, since accuracy would be low in image sets in which the position is fixed in the whole image sets, such as medical images. Techniques such as PuzzleMix and SnapMix are likely to be more effective for tasks in which the subtle points hold importance.
Further hopes
I will continue to use the systems supported for Z by HP Data Science Global Ambassadors to compare and test methods of various papers in CV competitions.
Have a Question?
Contact Sales Support.
Follow Z by HP on Social Media
Need Help in Choosing the Best
Z Workstation Solutions?
Need Support for Your Z Workstation?
Disclaimers
Product may differ from images depicted.
Product images are for illustration purposes only, product availability and colours may vary by country.
© HP Development Company, L.P. The Information contained herein is subject to change without notice. Warranties for HP products and services are set out in the express warranty statements accompanying such products and services. In addition, our products and services come with guarantees that cannot be excluded under the Australian Consumer Law. Subject to the foregoing, nothing herein should be construed as constituting an additional warranty. HP shall not be liable for technical or editorial errors or omissions contained herein.