PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning

Lifelong learning has attracted much attention, but existing works still struggle to fight catastrophic forgetting and accumulate knowledge over long stretches of incremental learning. In this work, we propose PODNet, a model inspired by representation learning... (read more)

PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Incremental Learning CIFAR-100 - 50 classes + 10 steps of 5 classes PODNet (CNN) Average Incremental Accuracy 63.19 # 1
Incremental Learning CIFAR-100 - 50 classes + 25 steps of 2 classes PODNet Average Incremental Accuracy 60.72 # 1
Incremental Learning CIFAR-100 - 50 classes + 50 steps of 1 class PODNet Average Incremental Accuracy 57.98 # 1
Incremental Learning CIFAR-100 - 50 classes + 5 steps of 10 classes PODNet (CNN) Average Incremental Accuracy 64.83 # 1
Incremental Learning ImageNet-100 - 50 classes + 10 steps of 5 classes PODNet Average Incremental Accuracy 73.14 # 1
Incremental Learning ImageNet-100 - 50 classes + 25 steps of 2 classes PODNet Average Incremental Accuracy 67.28 # 1
Incremental Learning ImageNet-100 - 50 classes + 50 steps of 1 class PODNet Average Incremental Accuracy 62.08 # 1
Incremental Learning ImageNet-100 - 50 classes + 5 steps of 10 classes PODNet Average Incremental Accuracy 75.82 # 1
Incremental Learning ImageNet - 500 classes + 50 steps of 10 classes PODNet Average Incremental Accuracy 64.13 # 1
Incremental Learning ImageNet - 500 classes + 5 steps of 100 classes PODNet Average Incremental Accuracy 66.95 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet