Modulating CNN Features with Pre-Trained ViT Representations for Open-Vocabulary Object Detection

원문 초록

Owing to large-scale image-text contrastive training, pre-trained vision language model (VLM) like CLIP shows superior open-vocabulary recognition ability. Most existing open-vocabulary object detectors attempt to utilize the pre-trained VLM to attain generative representation. F-ViT uses the pre-trained visual encoder as the backbone network and freezes it during training. However, the frozen backbone doesn't benefit from the labeled data to strengthen the representation. Therefore, we propose a novel two-branch backbone network design, named as ViT-Feature-Modulated Multi-Scale Convolutional network (VMCNet). VMCNet consists of a trainable convolutional branch, a frozen pre-trained ViT branch and a feature modulation module. The trainable CNN branch could be optimized with labeled data while the frozen pre-trained ViT branch could keep the representation ability derived from large-scale pre-training. Then, the proposed feature modulation module could modulate the multi-scale CNN features with the representations from ViT branch. With the proposed mixed structure, detector is more likely to discover novel categories. Evaluated on two popular benchmarks, our method boosts the detection performance on novel category and outperforms the baseline. On OV-COCO, the proposed method achieves 44.3 AP$_{50}^{\mathrm{novel}}$ with ViT-B/16 and 48.5 AP$_{50}^{\mathrm{novel}}$ with ViT-L/14. On OV-LVIS, VMCNet with ViT-B/16 and ViT-L/14 reaches 27.8 and 38.4 mAP$_{r}$.