Learning to solve complex sequences of tasks--while both leveraging transfer and avoiding catastrophic forgetting--remains a key obstacle to achieving human-level intelligence. The progressive networks approach represents a step forward in this direction: they are immune to forgetting and can leverage prior knowledge via lateral connections to previously learned features... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Continual Learning CUBS (Fine-grained 6 Tasks) ProgressiveNet Accuracy 78.94 # 4
Continual Learning Flowers (Fine-grained 6 Tasks) ProgressiveNet Accuracy 93.41 # 3
Continual Learning ImageNet (Fine-grained 6 Tasks) ProgressiveNet Accuracy 76.16 # 1
Continual Learning Sketch (Fine-grained 6 Tasks) ProgressiveNet Accuracy 76.35 # 3
Continual Learning Stanford Cars (Fine-grained 6 Tasks) ProgressiveNet Accuracy 89.21 # 3
Continual Learning Wikiart (Fine-grained 6 Tasks) ProgressiveNet Accuracy 74.94 # 2

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