DF-GAN: Deep Fusion Generative Adversarial Networks for Text-to-Image Synthesis

By Ming Tao, Hao Tang, Songsong Wu, Nicu Sebe, Fei Wu, Xiaoyuan Jing. 2020

224 citations recorded by the source corpus.

Subfields: Generative Models, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

In Multimodal Learning

Citations in the corpus

Hierarchical Text-Conditional Image Generation with CLIP Latents (2022, background): “Many previous works have trained GANs [21] on publicly available image captioning datasets to produce text-conditional image samples [56, 63, 49, 58, 57].”
Zero-Shot Text-to-Image Generation (2021, methodology): “, 2019), and DF-GAN (Tao et al., 2020), the last of which reports the best Inception Score (Salimans et al.”
Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors (2022, methodology): “64 - - - - DF-GAN [54] 21 .”
Towards Language-Free Training for Text-to-Image Generation (2021, methodology): “We compare L AFITE against a series of competitive systems: AttnGAN [51], Obj-GAN [23], DM-GAN [57], OP-GAN [13], DF-GAN [42] and XMC-GAN [54].”
CogView: Mastering Text-to-Image Generation via Transformers (2021, background): “DM-GAN [55] and DF-GAN [45] introduced new architectures, e.g. dyanmic memory or deep fusion block, for better image reﬁnement.”
CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP (2022, methodology): “DF-GAN [35], DM-GAN [45] and AttnGAN [39] represent the traditional approaches which use CNN generator to directly generate images with a textual condition.”
CM3: A Causal Masked Multimodal Model of the Internet (2022, neutral): “…cases of our proposed zero-shot captioning are due Model FID Zero-shot FID AttnGAN (Xu et al., 2017) 35.49 DM-GAN (Zhu et al., 2019) 32.64 DF-GAN (Tao et al., 2020) 21.42 DM-GAN + CL (Ye et al., 2021) 20.79 XMC-GAN (Zhang et al., 2021) 9.33 LAFITE (Zhou et al., 2021) 8.12 DALL-E (Ramesh et al.,…”
Improving Text-to-Image Synthesis Using Contrastive Learning (2021, methodology): “Most of the recent works [45, 46, 42, 13, 23, 48, 43, 18, 22, 17, 1, 12, 6, 19, 33, 4] on the text-to-image synthesis problem are based on GANs.”
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (2022, background): “[69] Ming Tao, Hao Tang, Songsong Wu, Nicu Sebe, Xiao-Yuan Jing, Fei Wu, and Bingkun Bao.”
UFC-BERT: Unifying Multi-Modal Controls for Conditional Image Synthesis (2021, methodology): “First, we compare our UFC-BERT with GAN-based text-to-image models AttnGAN [62], ControlGAN [30], DF-GAN [54], DM-GAN [69] and TediGAN [61] on the Multi-Modal CelebA-HQ dataset.”
Ablating Concepts in Text-to-Image Diffusion Models (2023, background): “Text-to-image synthesis has advanced significantly since the seminal works [82, 37], thanks to improvements in model architectures [77, 81, 68, 75, 28, 15, 74, 29, 57, 16], generative modeling techniques [52, 27, 54, 56, 4, 43, 14, 66], and availability of large-scale datasets [59].”
Multi-Concept Customization of Text-to-Image Diffusion (2022, methodology): “While earlier works [26,56,67, 78, 80, 87] were limited to a few classes [38, 71], recent text-to-image models [11,45,53,54,57,60,79], trained on extremely large-scale data, have demonstrated remarkable generalization ability.”
Lafite2: Few-shot Text-to-Image Generation (2022, methodology): “We compare our methods with different fully-supervised methods including AttnGAN [39], Obj-GAN [17], DM-GAN [45], OP-GAN [10], DF-GAN [34], XMC-GAN [41], L AFITE [44] and Make-A-Scene [7].”
Cycle-Consistent Inverse GAN for Text-to-Image Synthesis (2021, methodology): “Text-to-image synthesis [6, 20, 21, 26, 35–37 , 42 ] text descriptions, typically based on the Generative Adversarial Networks (GANs) approaches.”
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion (2022, background): “Typically, a conditional model is trained to reproduce samples from given paired image-caption datasets (Zhu et al., 2019; Tao et al., 2020), leveraging attention mechanisms (Xu et al., 2018) or cross-modal contrastive approaches (Zhang et al., 2021; Ye et al., 2021).”