Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise

TL;DR

This paper evaluates the performance of various vision transformer models under label noise in active learning scenarios, highlighting the robustness of larger models and the impact of patch size on accuracy and calibration.

Contribution

It provides a comprehensive comparison of vision transformer configurations under label noise, offering practical insights for deploying efficient models in noisy, resource-limited settings.

Findings

Larger ViT models outperform smaller ones in accuracy and calibration under noise.

Swin Transformers show weaker robustness to label noise across configurations.

Smaller patch sizes do not always improve performance and increase computational costs.

Abstract

Fine-tuning pre-trained convolutional neural networks on ImageNet for downstream tasks is well-established. Still, the impact of model size on the performance of vision transformers in similar scenarios, particularly under label noise, remains largely unexplored. Given the utility and versatility of transformer architectures, this study investigates their practicality under low-budget constraints and noisy labels. We explore how classification accuracy and calibration are affected by symmetric label noise in active learning settings, evaluating four vision transformer configurations (Base and Large with 16x16 and 32x32 patch sizes) and three Swin Transformer configurations (Tiny, Small, and Base) on CIFAR10 and CIFAR100 datasets, under varying label noise rates. Our findings show that larger ViT models (ViTl32 in particular) consistently outperform their smaller counterparts in both accuracy and calibration, even under moderate to high label noise, while Swin Transformers exhibit weaker robustness across all noise levels. We find that smaller patch sizes do not always lead to better performance, as ViTl16 performs consistently worse than ViTl32 while incurring a higher computational cost. We also find that information-based Active Learning strategies only provide meaningful accuracy improvements at moderate label noise rates, but they result in poorer calibration compared to models trained on randomly acquired labels, especially at high label noise rates. We hope these insights provide actionable guidance for practitioners looking to deploy vision transformers in resource-constrained environments, where balancing model complexity, label noise, and compute efficiency is critical in model fine-tuning or distillation.