Incremental Learning
Incremental learning aims to develop artificial intelligence systems that can continuously learn from new data to address new tasks while retaining knowledge acquired from previous tasks. This approach updates the model constantly, enabling it to adapt to new environments without forgetting old knowledge, thereby enhancing the system's long-term adaptability and efficiency, which holds significant application value.
CIFAR-100 - 40 classes + 60 steps of 1 class (Exemplar-free)
FeTrIL
CIFAR-100 - 50 classes + 10 steps of 5 classes
DER(Standard ResNet-18)
CIFAR-100 - 50 classes + 2 steps of 25 classes
TCIL
CIFAR-100 - 50 classes + 25 steps of 2 classes
RMM (Modified ResNet-32)
CIFAR-100 - 50 classes + 5 steps of 10 classes
PPCA-SWSL
CIFAR-100 - 50 classes + 50 steps of 1 class
PODNet
CIFAR-100-B0(5steps of 20 classes)
CIFAR100-B0(10steps of 10 classes)
CIFAR100B020Step(5ClassesPerStep)
CIFAR100B050S(2ClassesPerStep)
DER(ResNet-18)
ImageNet - 10 steps
ImageNet-100 - 50 classes + 10 steps of 5 classes
RMM (ResNet-18)
ImageNet-100 - 50 classes + 25 steps of 2 classes
ImageNet-100 - 50 classes + 5 steps of 10 classes
RMM (ResNet-18)
ImageNet-100 - 50 classes + 50 steps of 1 class
PODNet
ImageNet-10k - 5225 classes + 5 steps of 1045 classes
PPCA-CLIP
ImageNet - 500 classes + 10 steps of 50 classes
PODNet
ImageNet - 500 classes + 25 steps of 20 classes
RMM (ResNet-18)
ImageNet - 500 classes + 5 steps of 100 classes
RMM (ResNet-18)
ImageNet100 - 10 steps
RMM (ResNet-18)
ImageNet100 - 20 steps
FOSTER
MLT17
MRM