List your company
ResearchFormerly WizWand

Active Learning Image Classification on CIFAR-10+100 1.0 (test)

80.9AccuracyTD-FT (Ours)
25.7840.0954.468.71Oct 29, 2025
Updated 8mo ago

Evaluation results

MethodLinks
TD-FT (Ours)Acquisition Strategy=Power batch acquisition, Representation Learning Method=Task-Driven Fine-Tuning, Encoder Backbone=ResNet502025.1080.9
TD-FT RandomAcquisition Strategy=Random, Representation Learning Method=Task-Driven Fine-Tuning, Encoder Backbone=ResNet502025.1077.14
US+EPIG (SimCLRv2)Acquisition Strategy=EPIG, Representation Learning Method=SimCLRv2, Encoder Backbone=ResNet502025.1076.19
US Random (SimCLRv2)Acquisition Strategy=Random, Representation Learning Method=SimCLRv2, Encoder Backbone=ResNet502025.1074.6
TD-SPLIT (Ours)Acquisition Strategy=Power batch acquisition, Representation Learning Method=Task-Driven SPLIT, Encoder Backbone=ResNet502025.1059.84
GALAXYAcquisition Strategy=GALAXY, Representation Learning Method=Original Baseline, Encoder Backbone=ResNet502025.1055.28
TD-SPLIT RandomAcquisition Strategy=Random, Representation Learning Method=Task-Driven SPLIT, Encoder Backbone=ResNet502025.1054.9
Cluster MarginAcquisition Strategy=Cluster Margin, Representation Learning Method=Original Baseline, Encoder Backbone=ResNet502025.1032.79
SIMILARAcquisition Strategy=SIMILAR, Representation Learning Method=Original Baseline, Encoder Backbone=ResNet502025.1030.87
US+EPIG (VAE)Acquisition Strategy=EPIG, Representation Learning Method=VAE, Encoder Backbone=ResNet-VAE2025.1030.47
US Random (VAE)Acquisition Strategy=Random, Representation Learning Method=VAE, Encoder Backbone=ResNet-VAE2025.1027.9