List your company
ResearchFormerly WizWand

Class Incremental Learning on CUB

90.6Avg AccuracyRanPAC
-2.68821.53145.7569.969Jul 5, 2023Aug 11, 2023Sep 17, 2023Oct 24, 2023Nov 30, 2023Jan 6, 2024Feb 13, 2024
Updated 8mo ago

Evaluation results

MethodLinks
RanPACNumber of tasks (T)=52023.0790.6
RanPACNumber of tasks (T)=102023.0790.3
RanPACPhase Configuration=No Phase 12023.0789.9
RanPACNumber of tasks (T)=202023.0789.7
RanPAC-impBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.0289.6
RanPAC-impBackbone=ViT-B/16, Pre-training=ImageNet-21K, Task Setting=2 init classes, 1 class per task2024.0289.6
RanDumbBackbone=ViT-B/16, Pre-training=ImageNet-21K, Task Setting=2 init classes, 1 class per task2024.0288.5
RanDumbBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.0288
AdaMNumber of tasks (T)=52023.0787.3
RanPACBackbone=ViT-B/16, Pre-training=ImageNet-21K, Task Setting=2 init classes, 1 class per task2024.0287.2
AdaMNumber of tasks (T)=102023.0787.1
NCMNumber of tasks (T)=52023.0787
NCMNumber of tasks (T)=102023.0787
NCMNumber of tasks (T)=202023.0786.9
FosterBackbone=ViT-B/16, Pre-training=ImageNet-21K, Task Setting=2 init classes, 1 class per task2024.0286.9
AdaMNumber of tasks (T)=202023.0786.7
NCMPhase Configuration=No Phase 12023.0786.7
Adam-AdaptBackbone=ViT-B/16, Pre-training=ImageNet-21K, Task Setting=2 init classes, 1 class per task2024.0286.7
FosterBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.0286.6
Adam-FTBackbone=ViT-B/16, Pre-training=ImageNet-21K, Task Setting=2 init classes, 1 class per task2024.0286.5
NCMBackbone=ViT-B/16, Pre-training=ImageNet-21K, Task Setting=2 init classes, 1 class per task2024.0286.5
Adam-SSFBackbone=ViT-B/16, Pre-training=ImageNet-21K, Task Setting=2 init classes, 1 class per task2024.0286.2
Adam-SSFBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.0285.6
Adam-AdaptBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.0285.2
Adam-FTBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.0285.2
NCMBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.0284.8
SLCABackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.0284.7
Adam-VPTBackbone=ViT-B/16, Pre-training=ImageNet-21K, Task Setting=2 init classes, 1 class per task2024.0284
Adam-VPTBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.0283.8
SLCABackbone=ViT-B/16, Pre-training=ImageNet-21K, Task Setting=2 init classes, 1 class per task2024.0282.1
MemoBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.0281.4
RanPACBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.0277.7
DualPromptNumber of tasks (T)=52023.0773.7
iCARLBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.0272.4
iCARLBackbone=ViT-B/16, Pre-training=ImageNet-21K, Task Setting=2 init classes, 1 class per task2024.0271.6
L2PNumber of tasks (T)=52023.0769.7
DualPromptNumber of tasks (T)=102023.0768.5
DualPromptNumber of tasks (T)=202023.0766.5
L2PNumber of tasks (T)=102023.0765.2
L2PNumber of tasks (T)=202023.0756.3
CODA-PromptBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.021.9
L2PBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.021.4
FinetuneBackbone=ViT-B/16, Pre-training=ImageNet-21K, Task Setting=2 init classes, 1 class per task2024.021.2
FinetuneBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.021
DualPromptBackbone=ViT-B/16, Pre-training=ImageNet-1K, Task Setting=2 init classes, 1 class per task2024.020.9