English

LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation

Computer Vision and Pattern Recognition 2022-06-03 v2

Abstract

Text-guided image manipulation tasks have recently gained attention in the vision-and-language community. While most of the prior studies focused on single-turn manipulation, our goal in this paper is to address the more challenging multi-turn image manipulation (MTIM) task. Previous models for this task successfully generate images iteratively, given a sequence of instructions and a previously generated image. However, this approach suffers from under-generation and a lack of generated quality of the objects that are described in the instructions, which consequently degrades the overall performance. To overcome these problems, we present a novel architecture called a Visually Guided Language Attention GAN (LatteGAN). Here, we address the limitations of the previous approaches by introducing a Visually Guided Language Attention (Latte) module, which extracts fine-grained text representations for the generator, and a Text-Conditioned U-Net discriminator architecture, which discriminates both the global and local representations of fake or real images. Extensive experiments on two distinct MTIM datasets, CoDraw and i-CLEVR, demonstrate the state-of-the-art performance of the proposed model.

Keywords

Cite

@article{arxiv.2112.13985,
  title  = {LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation},
  author = {Shoya Matsumori and Yuki Abe and Kosuke Shingyouchi and Komei Sugiura and Michita Imai},
  journal= {arXiv preprint arXiv:2112.13985},
  year   = {2022}
}
R2 v1 2026-06-24T08:33:17.758Z