Sampling Bag of Views for Open-Vocabulary Object Detection
This work addresses efficiency and performance issues in open-vocabulary object detection for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of noisy compositional structures in open-vocabulary object detection by proposing a concept-based alignment method that groups contextually related concepts into a bag and adjusts their scale, achieving improvements of 2.6 box AP50 and 0.5 mask AP over prior work on novel categories in COCO and LVIS benchmarks while reducing CLIP computation by 80.3%.
Existing open-vocabulary object detection (OVD) develops methods for testing unseen categories by aligning object region embeddings with corresponding VLM features. A recent study leverages the idea that VLMs implicitly learn compositional structures of semantic concepts within the image. Instead of using an individual region embedding, it utilizes a bag of region embeddings as a new representation to incorporate compositional structures into the OVD task. However, this approach often fails to capture the contextual concepts of each region, leading to noisy compositional structures. This results in only marginal performance improvements and reduced efficiency. To address this, we propose a novel concept-based alignment method that samples a more powerful and efficient compositional structure. Our approach groups contextually related ``concepts'' into a bag and adjusts the scale of concepts within the bag for more effective embedding alignment. Combined with Faster R-CNN, our method achieves improvements of 2.6 box AP50 and 0.5 mask AP over prior work on novel categories in the open-vocabulary COCO and LVIS benchmarks. Furthermore, our method reduces CLIP computation in FLOPs by 80.3% compared to previous research, significantly enhancing efficiency. Experimental results demonstrate that the proposed method outperforms previous state-of-the-art models on the OVD datasets.