arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.04072cs.CV
收藏

超越限界框:多模态知识学习的目标检测

Beyond Bounding Box: Multimodal Knowledge Learning for Object Detection

Alibaba Group(阿里巴巴集团)

Weixin Feng, Xingyuan Bu, Chenchen Zhang, Xubin Li

摘要:

多模态监督在许多视觉语言理解任务中取得了可喜的成果,其中语言作为识别和定位实例的提示或上下文起着至关重要的作用。然而,由于人类标注的语言语料库的缺陷,多模态监督仍然是未开发的全监督目标检测场景。本文利用语言提示的优势,将有效的、无偏的语言监督引入到目标检测中,提出了一种多模态知识学习(\textbf{MKL})机制,该机制需要从语言监督中学习知识。具体来说,我们设计的提示,并填写他们的限界框注释,以产生包含广泛的提示和上下文的实例识别和定位的描述。然后通过最大化图像和对象两级的跨模态互信息,将语言知识提取到检测模型中。此外,生成的描述被操纵以产生硬底片,以进一步提高检测器的性能。大量的实验表明,该方法在MS-COCO和OpenImages数据集上获得了1.6% $\sim$ 2.1%的一致性能增益,达到了最先进的水平.

英文摘要:

Multimodal supervision has achieved promising results in many visual language understanding tasks, where the language plays an essential role as a hint or context for recognizing and locating instances. However, due to the defects of the human-annotated language corpus, multimodal supervision remains unexplored in fully supervised object detection scenarios. In this paper, we take advantage of language prompt to introduce effective and unbiased linguistic supervision into object detection, and propose a new mechanism called multimodal knowledge learning (\textbf{MKL}), which is required to learn knowledge from language supervision. Specifically, we design prompts and fill them with the bounding box annotations to generate descriptions containing extensive hints and context for instances recognition and localization. The knowledge from language is then distilled into the detection model via maximizing cross-modal mutual information in both image- and object-level. Moreover, the generated descriptions are manipulated to produce hard negatives to further boost the detector performance. Extensive experiments demonstrate that the proposed method yields a consistent performance gain by 1.6\% $\sim$ 2.1\% and achieves state-of-the-art on MS-COCO and OpenImages datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑