@article{ART003370675},
author={Du-Hwan Hur and Dong-Hyun Kim and Seung-Hwan Bae},
title={Rethinking PEFT Evaluation: A Class-Balanced Protocol Across Data Scales for Fair Comparison},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2026},
volume={31},
number={8},
pages={17-30}
TY - JOUR
AU - Du-Hwan Hur
AU - Dong-Hyun Kim
AU - Seung-Hwan Bae
TI - Rethinking PEFT Evaluation: A Class-Balanced Protocol Across Data Scales for Fair Comparison
JO - Journal of The Korea Society of Computer and Information
PY - 2026
VL - 31
IS - 8
PB - The Korean Society Of Computer And Information
SP - 17
EP - 30
SN - 1598-849X
AB - In this paper, we propose a class-balanced evaluation protocol across data scales based on the VTAB-1k benchmark to analyze Parameter-Efficient Fine-Tuning (PEFT) under the extreme data scarcity and class imbalance of real-world domains such as medical and satellite imagery. The pipeline independently controls data scale (10%–100%) and class balance, benchmarking Adapter, LoRA, and Visual Prompt Tuning (VPT) on 19 tasks over a frozen ViT backbone, together with full fine-tuning and linear-probing baselines and a recent variant, DoRA. A clear performance crossover is observed: VPT, strong in specialized and structured domains, dominates below the 50% scale, whereas LoRA, strong in natural domains, prevails as data increases. Class balancing trades a small amount of overall Top-1 accuracy for higher balanced accuracy in low-data regimes, and its effect vanishes at larger scales as the balanced subset converges to the original distribution. These controlled results demonstrate that no single PEFT method is universally optimal, and the resulting guidelines support the practical deployment of PEFT in data-limited applications such as medical imaging, remote sensing, and industrial inspection.
KW - Parameter-Efficient Fine-Tuning;Low-Data Learning;Visual Prompt Tuning;Low-Rank Adaptation;Adapter
DO -
UR -
ER -
Du-Hwan Hur, Dong-Hyun Kim and Seung-Hwan Bae. (2026). Rethinking PEFT Evaluation: A Class-Balanced Protocol Across Data Scales for Fair Comparison. Journal of The Korea Society of Computer and Information, 31(8), 17-30.
Du-Hwan Hur, Dong-Hyun Kim and Seung-Hwan Bae. 2026, "Rethinking PEFT Evaluation: A Class-Balanced Protocol Across Data Scales for Fair Comparison", Journal of The Korea Society of Computer and Information, vol.31, no.8 pp.17-30.
Du-Hwan Hur, Dong-Hyun Kim, Seung-Hwan Bae "Rethinking PEFT Evaluation: A Class-Balanced Protocol Across Data Scales for Fair Comparison" Journal of The Korea Society of Computer and Information 31.8 pp.17-30 (2026) : 17.
Du-Hwan Hur, Dong-Hyun Kim, Seung-Hwan Bae. Rethinking PEFT Evaluation: A Class-Balanced Protocol Across Data Scales for Fair Comparison. 2026; 31(8), 17-30.
Du-Hwan Hur, Dong-Hyun Kim and Seung-Hwan Bae. "Rethinking PEFT Evaluation: A Class-Balanced Protocol Across Data Scales for Fair Comparison" Journal of The Korea Society of Computer and Information 31, no.8 (2026) : 17-30.
Du-Hwan Hur; Dong-Hyun Kim; Seung-Hwan Bae. Rethinking PEFT Evaluation: A Class-Balanced Protocol Across Data Scales for Fair Comparison. Journal of The Korea Society of Computer and Information, 31(8), 17-30.
Du-Hwan Hur; Dong-Hyun Kim; Seung-Hwan Bae. Rethinking PEFT Evaluation: A Class-Balanced Protocol Across Data Scales for Fair Comparison. Journal of The Korea Society of Computer and Information. 2026; 31(8) 17-30.
Du-Hwan Hur, Dong-Hyun Kim, Seung-Hwan Bae. Rethinking PEFT Evaluation: A Class-Balanced Protocol Across Data Scales for Fair Comparison. 2026; 31(8), 17-30.
Du-Hwan Hur, Dong-Hyun Kim and Seung-Hwan Bae. "Rethinking PEFT Evaluation: A Class-Balanced Protocol Across Data Scales for Fair Comparison" Journal of The Korea Society of Computer and Information 31, no.8 (2026) : 17-30.
