The Pursuit of Knowledge: Discovering and Localizing Novel Categories using Dual Memory
This work addresses the problem of discovering novel objects in unlabeled data for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles object category discovery and localization in cluttered scenes by leveraging prior knowledge through dual memory modules, achieving results on the challenging COCO dataset.
We tackle object category discovery, which is the problem of discovering and localizing novel objects in a large unlabeled dataset. While existing methods show results on datasets with less cluttered scenes and fewer object instances per image, we present our results on the challenging COCO dataset. Moreover, we argue that, rather than discovering new categories from scratch, discovery algorithms can benefit from identifying what is already known and focusing their attention on the unknown. We propose a method that exploits prior knowledge about certain object types to discover new categories by leveraging two memory modules, namely Working and Semantic memory. We show the performance of our detector on the COCO minival dataset to demonstrate its in-the-wild capabilities.