Augmenting Zero-Shot Detection Training with Image Labels

no code implementations • 12 Jun 2023 • Katharina Kornmeier, Ulla Scheler, Pascal Herrmann

Compared to only training on detection data, we see a significant gain by adding image label data of 3. 3 mAP for the 65/15 split on COCO on the unseen classes, i. e., we more than double the gain of related work.

Image Classification

Self-Paced Absolute Learning Progress as a Regularized Approach to Curriculum Learning

no code implementations • 9 Jun 2023 • Tobias Niehues, Ulla Scheler, Pascal Klink

Curricula based on Absolute Learning Progress (ALP) have proven successful in different environments, but waste computation on repeating already learned behaviour in new tasks.

reinforcement-learning