Tied-Augment: Controlling Representation Similarity Improves Data Augmentation

Authors: Emirhan Kurtuluş, Zichao Li, Yann Dauphin, Ekin Dogus Cubuk

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental To show the effectiveness of Tied-Augment, we experiment with training from-scratch on CIFAR-10, CIFAR-100, and Image Net. We extend these tests with finetuning and few-epoch / low-data regimes to simulate more realistic scenarios, where the amount of domain-specific data or available compute is limited. Lastly, we show that Tied-Augment significantly improves the performance of state-of-the-art methods (e.g. mixup and SAM) and can be used for semisupervised learning (e.g. Fix Match).
Researcher Affiliation Collaboration 1Stanford University 2Cagaloglu Anadolu Lisesi 3Google Research, Brain Team. Correspondence to: Emirhan Kurtulus <emirhank@stanford.edu>, Ekin D. Cubuk <cubuk@google.com>.
Pseudocode Yes Figure 1. Python code for Tied-Augment based on Num Py.
Open Source Code Yes We open source our code at https://github.com/ ekurtulus/tied-augment/tree/main
Open Datasets Yes To show the effectiveness of Tied-Augment, we experiment with training from-scratch on CIFAR-10, CIFAR-100, and Image Net. We extend these tests with finetuning and few-epoch / low-data regimes to simulate more realistic scenarios, where the amount of domain-specific data or available compute is limited.
Dataset Splits Yes For runs with epoch={1, 2, 5}, the learning rate and weight-decay were tuned to maximize the validation accuracy of the identity baseline (since in this regime identity baseline outperforms the Crop-Flip baseline). The learning rate and weight-decay hyperparameters for the 10 epoch models were tuned to maximize the validation set performance of the Crop-Flip baseline.
Hardware Specification Yes The numerical calculations reported in this paper were partially performed at TUBITAK ULAKBIM, High Performance and Grid Computing Center (TRUBA resources). ... we empirically observe an increase of roughly 30% increase on an Nvidia A100 on CIFAR-10.
Software Dependencies No Figure 1 mentions "Python code for Tied-Augment based on Num Py", but specific version numbers for Python or NumPy are not provided, nor are any other software dependencies with versions.
Experiment Setup Yes All Image Net models use a learning rate of 0.4 with a batch size of 1024, weight-decay rate of 1e-4. The Tied Rand Augment model that was trained for 90 epochs used Crop-Flip on first branch, and Rand Augment(N=2, M=9) on the other branch, with a Tied-weight of 4. The Tied Rand Augment Res Net-50 model that was trained for 360 epochs used Rand Augment(N=2, M=13) for the first branch and Rand Augment(N=2, M=9, P=0.5) for the second branch, with a Tied-weight of 12.0. The Tied-Rand Augment Res Net-200 model used Rand Augment(N=2, M=13) for both branches with a Tied-weight of 12.0. All Tied-Augment Image Net models trained for 90 epochs used a Tied-weight of 4, and models trained for longer used a Tied-weight of 12. The optimal Tied-weight for Tiedmixup on Imagenet was 50.