Parameter-efficient fine-tuning (LoRA family)
MC Dropout
Superseded baseline#114 of 1,113 most-superseded
Superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 2 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating MC Dropout. Values are copied from the source paper's tables — verify against the cited paper.
IVON beats MC Dropout
10.6 vs 20.2
Expected Calibration Error (ECE) · [All datasets]
Variational Low-Rank Adaptation Using IVONIVON@mean beats MC Dropout
17.2 vs 20.2
Expected Calibration Error (ECE) · [All datasets]
Variational Low-Rank Adaptation Using IVONLoRA-Ensemble beats MC Dropout
82.5 vs 77.1
Accuracy · [16-member ensemble on CIFAR-100]
LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks