Retrieval-Augmented Open-Vocabulary Object Detection (2404.05687v1)

Abstract: Open-vocabulary object detection (OVD) has been studied with Vision-LLMs (VLMs) to detect novel objects beyond the pre-trained categories. Previous approaches improve the generalization ability to expand the knowledge of the detector, using 'positive' pseudo-labels with additional 'class' names, e.g., sock, iPod, and alligator. To extend the previous methods in two aspects, we propose Retrieval-Augmented Losses and visual Features (RALF). Our method retrieves related 'negative' classes and augments loss functions. Also, visual features are augmented with 'verbalized concepts' of classes, e.g., worn on the feet, handheld music player, and sharp teeth. Specifically, RALF consists of two modules: Retrieval Augmented Losses (RAL) and Retrieval-Augmented visual Features (RAF). RAL constitutes two losses reflecting the semantic similarity with negative vocabularies. In addition, RAF augments visual features with the verbalized concepts from a LLM. Our experiments demonstrate the effectiveness of RALF on COCO and LVIS benchmark datasets. We achieve improvement up to 3.4 box AP${50}^{\text{N}}$ on novel categories of the COCO dataset and 3.6 mask AP${\text{r}}$ gains on the LVIS dataset. Code is available at https://github.com/mlvlab/RALF .