Whether you can locate or not? Interactive Referring Expression Generation
This work addresses the challenge of improving referring expression generation for computer vision applications, though it is incremental by building on existing REG and REC models.
The paper tackles the problem of generating unambiguous referring expressions for objects in visual scenes by proposing an Interactive REG model that interacts with a comprehension model to gradually modify expressions, achieving state-of-the-art performance on benchmark datasets like RefCOCO, RefCOCO+, and RefCOCOg.
Referring Expression Generation (REG) aims to generate unambiguous Referring Expressions (REs) for objects in a visual scene, with a dual task of Referring Expression Comprehension (REC) to locate the referred object. Existing methods construct REG models independently by using only the REs as ground truth for model training, without considering the potential interaction between REG and REC models. In this paper, we propose an Interactive REG (IREG) model that can interact with a real REC model, utilizing signals indicating whether the object is located and the visual region located by the REC model to gradually modify REs. Our experimental results on three RE benchmark datasets, RefCOCO, RefCOCO+, and RefCOCOg show that IREG outperforms previous state-of-the-art methods on popular evaluation metrics. Furthermore, a human evaluation shows that IREG generates better REs with the capability of interaction.