Abstract
Pretrained vision-language models, such as CLIP, have demonstrated strong generalization capabilities, making them promising tools in the realm of zero-shot visual recognition. Visual relation detection (VRD) is a typical task that identifies relationship (or interaction) types between object pairs within an image. However, naively utilizing CLIP with prevalent class-based prompts for zero-shot VRD has several weaknesses, e.g., it struggles to distinguish between different fine-grained relation types and it neglects essential spatial information of two objects. To this end, we propose a novel method for zero-shot VRD: RECODE, which solves RElation detection via COmposite DEscription prompts. Specifically, RECODE first decomposes each predicate category into subject, object, and spatial components. Then, it leverages large language models (LLMs) to generate description-based prompts (or visual cues) for each component. Different visual cues enhance the discriminability of similar relation categories from different perspectives, which significantly boosts performance in VRD. To dynamically fuse different cues, we further introduce a chain-of-thought method that prompts LLMs to generate reasonable weights for different visual cues. Extensive experiments on four VRD benchmarks have demonstrated the effectiveness and interpretability of RECODE.
Abstract (translated)
训练有素的视觉语言模型,如CLIP,已经表现出强大的泛化能力,使其成为零次视觉识别领域有前途的工具。视觉关系检测(VRD)是一种常见的任务,该任务在图像中识别关系(或交互)类型的不同细节类型。然而,天真地使用基于类的Clip提示进行零次VRD有以下几个弱点,例如,它 struggle 很难区分不同细致的关系类型,并且它忽略了两个对象的重要空间信息。为此,我们提出了一种零次VRD的新型方法:RECODE,该方法通过合并描述提示解决关系检测。具体来说,RECODE首先将每个谓词类别分解为主题、对象和空间组件。然后,它利用大型语言模型(LLM)生成每个组件的描述性提示(或视觉提示)。不同的视觉提示增强从不同的角度识别类似关系类别的可区分性,这显著提高了VRD的性能。为了动态融合不同的提示,我们引入了一种思考链方法,promptLLM生成合理的视觉提示权重。在四个VRD基准实验中,已经证明了RECODE的有效性和解释性。
URL
https://arxiv.org/abs/2305.12476