TIDo: Source-free Task Incremental Learning in Non-stationary Environments
This work presents an incremental learning approach for autonomous agents to learn new tasks in a non-stationary environment. Updating a DNN model-based agent to learn new target tasks requires us to store past training data and needs a large labeled target task dataset. Few-shot task incremental le...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | This work presents an incremental learning approach for autonomous agents to
learn new tasks in a non-stationary environment. Updating a DNN model-based
agent to learn new target tasks requires us to store past training data and
needs a large labeled target task dataset. Few-shot task incremental learning
methods overcome the limitation of labeled target datasets by adapting trained
models to learn private target classes using a few labeled representatives and
a large unlabeled target dataset. However, the methods assume that the source
and target tasks are stationary. We propose a one-shot task incremental
learning approach that can adapt to non-stationary source and target tasks. Our
approach minimizes adversarial discrepancy between the model's feature space
and incoming incremental data to learn an updated hypothesis. We also use
distillation loss to reduce catastrophic forgetting of previously learned
tasks. Finally, we use Gaussian prototypes to generate exemplar instances
eliminating the need to store past training data. Unlike current work in task
incremental learning, our model can learn both source and target task updates
incrementally. We evaluate our method on various problem settings for
incremental object detection and disease prediction model update. We evaluate
our approach by measuring the performance of shared class and target private
class prediction. Our results show that our approach achieved improved
performance compared to existing state-of-the-art task incremental learning
methods. |
---|---|
DOI: | 10.48550/arxiv.2301.12055 |