AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Turbo Learning for CaptionBot and DrawingBot

Qiuyuan Huang, Pengchuan Zhang, Dapeng Wu, Lei Zhang

NeurIPS 2018 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 26 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Jointly train CaptionBot and DrawingBot with turbo learning rather than training them separatelyLSTM-XE CaptionBot and AttnGAN DrawingBot · COCO supervised, BLEU-4 rewardBLEU-4: 0.2684 -> 0.3168Improved
Jointly train CaptionBot and DrawingBot with turbo learning rather than training them separatelyAttnGAN DrawingBot · COCO supervised, BLEU-4 rewardInception score: 25.68 -> 26.69Improved
Jointly train CaptionBot and DrawingBot with turbo learning rather than training them separatelyLSTM-XE CaptionBot · COCO supervised, CIDEr-D rewardCIDEr-D: 0.7362 -> 0.7473Improved
Jointly train CaptionBot and DrawingBot with turbo learning rather than training them separatelyAttnGAN DrawingBot · COCO supervised, CIDEr-D rewardInception score: 25.68 -> 26.72Improved
Use turbo learning with unlabeled samples and cycle-generated pseudo-labelsLSTM-XE CaptionBot · COCO semi-supervised, 1,000 labeled and 112,287 unlabeled training samplesBLEU-4: 0.1036 -> 0.1832Improved
Use turbo learning with unlabeled samples and cycle-generated pseudo-labelsLSTM-RL CaptionBot · COCO semi-supervised, 1,000 labeled and 112,287 unlabeled training samplesCIDEr-D: 0.4924 -> 0.6954Improved
Use the perceptual-like semantic reconstruction loss instead of pixel-wise or DSSM reconstruction loss (ablation)Turbo learning for CaptionBot and DrawingBot · COCO supervisedperformanceImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy