Open-Vocabulary Object Detection with Meta Prompt Representation and Instance Contrastive Optimization
British Machine Vision Conference(2024)
摘要
Classical object detectors are incapable of detecting novel class objects
that are not encountered before. Regarding this issue, Open-Vocabulary Object
Detection (OVOD) is proposed, which aims to detect the objects in the candidate
class list. However, current OVOD models are suffering from overfitting on the
base classes, heavily relying on the large-scale extra data, and complex
training process. To overcome these issues, we propose a novel framework with
Meta prompt and Instance Contrastive learning (MIC) schemes. Firstly, we
simulate a novel-class-emerging scenario to help the prompt learner that learns
class and background prompts generalize to novel classes. Secondly, we design
an instance-level contrastive strategy to promote intra-class compactness and
inter-class separation, which benefits generalization of the detector to novel
class objects. Without using knowledge distillation, ensemble model or extra
training data during detector training, our proposed MIC outperforms previous
SOTA methods trained with these complex techniques on LVIS. Most importantly,
MIC shows great generalization ability on novel classes, e.g., with +4.3%
and +1.9% AP improvement compared with previous SOTA on COCO and
Objects365, respectively.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要