AI Paper Atlas

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

TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation

Tan M. Dinh, Rang Nguyen, Binh-Son Hua

ECCV 2022 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 17 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
add spectral normalization to the AttnGAN discriminators (AttnGAN++) (ablation)AttnGAN · CUBIS / FID / R-precision: IS 4.32 -> 4.78, FID 24.27 -> 15.01, RP 65.30 -> 77.31Improved
calibrate the Inception classifier with temperature scaling (IS to IS*) (ablation)Inception Score · CUBIS vs IS*: Counter Model IS 5.12 vs AttnGAN++ 4.78; IS* 13.05 vs 15.13Improved
calibrate the ImageNet Inception-v3 classifier (T=0.909) for IS* (ablation)Inception Score on Tiny ImageNet · Tiny ImageNetIS ranking: T = 0.909No clear effect
use CLIP encoders instead of DAMSM encoders for R-precision (ablation)R-precision · MS-COCOR-precision on real images: Real Images 67.35 -> 83.65; AttnGAN++ 96.39 -> 73.37Improved
compute SOA with Mask-RCNN instead of YOLO-v3 (ablation)SOA · MS-COCOSOA-C / SOA-I: CPGAN SOA-C 77.02 -> 82.25 versus Real Images 74.97 -> 89.98Improved
add contrastive learning (CL) to DM-GANDM-GAN · CUBFID / R-precision: FID 15.52 -> 14.57, RP 76.25 -> 69.80Mixed
add contrastive learning (CL) to DM-GANDM-GAN · MS-COCORanking score: 41.0 -> 51.5Improved
add contrastive learning (CL) to AttnGANAttnGAN · MS-COCORanking score: 29.0 -> 37.0Improved
include IS* in the rankingRanking score · MS-COCOIS* vs real images: IS* AttnGAN++ 54.63, CPGAN 59.64 vs Real Images 51.25Hurt
AttnGAN++ ranking score vs human evaluation (RS aligned with human score)Ranking score · MS-COCO human studyHuman score: AttnGAN 37.40 -> AttnGAN++ 45.01; RS 13.5 -> 28.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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