Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World

TL;DR

This paper introduces CaCao, a visually-prompted language model framework that enhances scene graph generation by addressing long-tail predicate issues and enabling zero-shot open-world predicate prediction.

Contribution

It proposes a novel cross-modal prompt boosting framework and an entangled prompt approach for zero-shot predicate generation, improving SGG performance and generalization.

Findings

CaCao boosts multiple SGG models across datasets.

Epic enables zero-shot unseen predicate prediction.

Framework is plug-and-play and model-agnostic.

Abstract

Scene Graph Generation (SGG) aims to extract <subject, predicate, object> relationships in images for vision understanding. Although recent works have made steady progress on SGG, they still suffer long-tail distribution issues that tail-predicates are more costly to train and hard to distinguish due to a small amount of annotated data compared to frequent predicates. Existing re-balancing strategies try to handle it via prior rules but are still confined to pre-defined conditions, which are not scalable for various models and datasets. In this paper, we propose a Cross-modal prediCate boosting (CaCao) framework, where a visually-prompted language model is learned to generate diverse fine-grained predicates in a low-resource way. The proposed CaCao can be applied in a plug-and-play fashion and automatically strengthen existing SGG to tackle the long-tailed problem. Based on that, we further introduce a novel Entangled cross-modal prompt approach for open-world predicate scene graph generation (Epic), where models can generalize to unseen predicates in a zero-shot manner. Comprehensive experiments on three benchmark datasets show that CaCao consistently boosts the performance of multiple scene graph generation models in a model-agnostic way. Moreover, our Epic achieves competitive performance on open-world predicate prediction. The data and code for this paper are publicly available.