Papers › Recurrent Affine Transformation for Text-to-image Synthesis

Recurrent Affine Transformation for Text-to-image Synthesis

22 Apr 2022arXiv:2204.10482archive 2025-07-28

Senmao Ye, Fei Liu, Minkui Tan

Text-to-image synthesis aims to generate natural images conditioned on text descriptions. The main difficulty of this task lies in effectively fusing text information into the image synthesis process. Existing methods usually adaptively fuse suitable text information into the synthesis process with multiple isolated fusion blocks (e.g., Conditional Batch Normalization and Instance Normalization). However, isolated fusion blocks not only conflict with each other but also increase the difficulty of training (see first page of the supplementary). To address these issues, we propose a Recurrent Affine Transformation (RAT) for Generative Adversarial Networks that connects all the fusion blocks with a recurrent neural network to model their long-term dependency. Besides, to improve semantic consistency between texts and synthesized images, we incorporate a spatial attention model in the discriminator. Being aware of matching image regions, text descriptions supervise the generator to synthesize more relevant image contents. Extensive experiments on the CUB, Oxford-102 and COCO datasets demonstrate the superiority of the proposed model in comparison to state-of-the-art models \footnote{https://github.com/senmaoy/Recurrent-Affine-Transformation-for-Text-to-image-Synthesis.git}

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

senmaoy/recurrent-affine-transformation-for-text-to-image-synthesis officialmentioned in papermentioned on GitHubpytorch report
senmaoy/RAT-Diffusion mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Text-to-Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Image Generation COCO (Common Objects in Context) RAT-GAN FID 14.6 #39 of 69 Archive leaderboard report
Text-to-Image Generation CUB RAT-GAN FID 10.21 #5 of 20 Archive leaderboard report
Text-to-Image Generation CUB RAT-GAN Inception score 5.36 #5 of 20 Archive leaderboard report
Text-to-Image Generation Oxford 102 Flowers RAT-GAN FID 16.04 #5 of 8 Archive leaderboard report
Text-to-Image Generation Oxford 102 Flowers RAT-GAN Inception score 4.09 #5 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AWAREBatch NormalizationConditional Batch NormalizationDense ConnectionsFeedforward Network

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections