Recurrent Topic-Transition GAN for Visual Paragraph Generation

TL;DR

This paper introduces RTT-GAN, a semi-supervised generative model that produces diverse, coherent visual paragraphs by reasoning over semantic regions and using adversarial training to ensure plausibility and topic coherence.

Contribution

It proposes a novel recurrent topic-transition GAN framework that integrates region-based attention and multi-level discriminators for semantically coherent paragraph generation.

Findings

RTT-GAN outperforms existing methods in generating realistic paragraphs.

The model effectively captures topic transitions and semantic diversity.

Qualitative results show interpretability and storytelling capability.

Abstract

A natural image usually conveys rich semantic content and can be viewed from different angles. Existing image description methods are largely restricted by small sets of biased visual paragraph annotations, and fail to cover rich underlying semantics. In this paper, we investigate a semi-supervised paragraph generative framework that is able to synthesize diverse and semantically coherent paragraph descriptions by reasoning over local semantic regions and exploiting linguistic knowledge. The proposed Recurrent Topic-Transition Generative Adversarial Network (RTT-GAN) builds an adversarial framework between a structured paragraph generator and multi-level paragraph discriminators. The paragraph generator generates sentences recurrently by incorporating region-based visual and language attention mechanisms at each step. The quality of generated paragraph sentences is assessed by multi-level adversarial discriminators from two aspects, namely, plausibility at sentence level and topic-transition coherence at paragraph level. The joint adversarial training of RTT-GAN drives the model to generate realistic paragraphs with smooth logical transition between sentence topics. Extensive quantitative experiments on image and video paragraph datasets demonstrate the effectiveness of our RTT-GAN in both supervised and semi-supervised settings. Qualitative results on telling diverse stories for an image also verify the interpretability of RTT-GAN.