PT4AL: Using Self-Supervised Pretext Tasks for Active Learning
Labeling a large set of data is expensive. Active learning aims to tackle this problem by asking to annotate only the most informative data from the unlabeled set. We propose a novel active learning approach that utilizes self-supervised pretext tasks and a unique data sampler to select data that ar...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Labeling a large set of data is expensive. Active learning aims to tackle
this problem by asking to annotate only the most informative data from the
unlabeled set. We propose a novel active learning approach that utilizes
self-supervised pretext tasks and a unique data sampler to select data that are
both difficult and representative. We discover that the loss of a simple
self-supervised pretext task, such as rotation prediction, is closely
correlated to the downstream task loss. Before the active learning iterations,
the pretext task learner is trained on the unlabeled set, and the unlabeled
data are sorted and split into batches by their pretext task losses. In each
active learning iteration, the main task model is used to sample the most
uncertain data in a batch to be annotated. We evaluate our method on various
image classification and segmentation benchmarks and achieve compelling
performances on CIFAR10, Caltech-101, ImageNet, and Cityscapes. We further show
that our method performs well on imbalanced datasets, and can be an effective
solution to the cold-start problem where active learning performance is
affected by the randomly sampled initial labeled set. |
---|---|
DOI: | 10.48550/arxiv.2201.07459 |