Papers › Cycle Text-To-Image GAN with BERT

Cycle Text-To-Image GAN with BERT

26 Mar 2020arXiv:2003.12137archive 2025-07-28

Trevor Tsue, Samir Sen, Jason Li

We explore novel approaches to the task of image generation from their respective captions, building on state-of-the-art GAN architectures. Particularly, we baseline our models with the Attention-based GANs that learn attention mappings from words to image features. To better capture the features of the descriptions, we then built a novel cyclic design that learns an inverse function to maps the image back to original caption. Additionally, we incorporated recently developed BERT pretrained word embeddings as our initial text featurizer and observe a noticeable improvement in qualitative and quantitative performance compared to the Attention GAN baseline.

PaperPDFCode

Code

suetAndTie/cycle-image-gan officialmentioned in papermentioned on GitHubpytorch report
BedirYilmaz/picturate-mwml mentioned on GitHubpytorch report
picturate/picturate mentioned on GitHubpytorch report
rightlit/cycle-image-gan-rev 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

Image GenerationWord Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTConvolutionDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

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