Can I read F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models on EtoBox?

F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models by Kuo, Weicheng; Cui, Yin; Gu, Xiuye; Piergiovanni, AJ; Angelova, Anelia is a scholarly article available to read on EtoBox.

What is F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models about?

We present F-VLM, a simple open-vocabulary object detection method built upon Frozen Vision and Language Models. F-VLM simplifies the current multi-stage training pipeline by eliminating the need for knowledge distillation or detection-tailored pretraining. Surprisingly, we observe that a frozen VLM: 1) retains the locality-sensitive features necessary for detection, and 2) is a strong region classifier. We finetune only the detector head and combine the detector and VLM outputs for each region at inference time. F-VLM shows compelling scaling behavior and achieves +6.5 mask AP improvement over the previous state of the art on novel categories of LVIS open-vocabulary detection benchmark. In addition, we demonstrate very competitive results on COCO open-vocabulary detection benchmark and cross-dataset transfer detection, in addition to significant training speed-up and compute savings. Code will be released at the https://sites.google.com/view/f-vlm/home

Author

Kuo, Weicheng; Cui, Yin; Gu, Xiuye; Piergiovanni, AJ; Angelova, Anelia

Published

2022

Language

EN