Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspective

by   Animesh Gupta, et al.

Coreset selection is among the most effective ways to reduce the training time of CNNs, however, only limited is known on how the resultant models will behave under variations of the coreset size, and choice of datasets and models. Moreover, given the recent paradigm shift towards transformer-based models, it is still an open question how coreset selection would impact their performance. There are several similar intriguing questions that need to be answered for a wide acceptance of coreset selection methods, and this paper attempts to answer some of these. We present a systematic benchmarking setup and perform a rigorous comparison of different coreset selection methods on CNNs and transformers. Our investigation reveals that under certain circumstances, random selection of subsets is more robust and stable when compared with the SOTA selection methods. We demonstrate that the conventional concept of uniform subset sampling across the various classes of the data is not the appropriate choice. Rather samples should be adaptively chosen based on the complexity of the data distribution for each class. Transformers are generally pretrained on large datasets, and we show that for certain target datasets, it helps to keep their performance stable at even very small coreset sizes. We further show that when no pretraining is done or when the pretrained transformer models are used with non-natural images (e.g. medical data), CNNs tend to generalize better than transformers at even very small coreset sizes. Lastly, we demonstrate that in the absence of the right pretraining, CNNs are better at learning the semantic coherence between spatially distant objects within an image, and these tend to outperform transformers at almost all choices of the coreset size.


Is it Time to Replace CNNs with Transformers for Medical Images?

Convolutional Neural Networks (CNNs) have reigned for a decade as the de...

Are Transformers More Robust Than CNNs?

Transformer emerges as a powerful tool for visual recognition. In additi...

How much pretraining data do language models need to learn syntax?

Transformers-based pretrained language models achieve outstanding result...

Study of positional encoding approaches for Audio Spectrogram Transformers

Transformers have revolutionized the world of deep learning, specially i...

Pretrained Transformers Improve Out-of-Distribution Robustness

Although pretrained Transformers such as BERT achieve high accuracy on i...

What Happens During Finetuning of Vision Transformers: An Invariance Based Investigation

The pretrain-finetune paradigm usually improves downstream performance o...

What is my math transformer doing? – Three results on interpretability and generalization

This paper investigates the failure cases and out-of-distribution behavi...

Please sign up or login with your details

Forgot password? Click here to reset