Fig. 3: Test accuracy per session on the keyword FSCIL task for prototypical and frozen baselines, with the accuracy on both base classes and incrementally-learned classes (left), and accuracy on all incrementally-learned classes only (right). | Nature Communications

Fig. 3: Test accuracy per session on the keyword FSCIL task for prototypical and frozen baselines, with the accuracy on both base classes and incrementally-learned classes (left), and accuracy on all incrementally-learned classes only (right).

From: The neurobench framework for benchmarking neuromorphic computing algorithms and systems

Fig. 3

Incremental session 0 refers to the accuracy on base classes after pre-training only. Shaded area represents 5th and 95th percentile on 100 runs. Frozen baselines with no adaptation do not learn incremental classes and thus have a fixed 0% accuracy for New Classes Performance.

Back to article page