AI Paper Atlas

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

Dual Adversarial Inference for Text-to-Image Synthesis

Qicheng Lao, Mohammad Havaei, Ahmad Pesaranghader, Francis Dutil, Lisa Di Jorio, Thomas Fevens

ICCV 2019 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 39 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 dual adversarial inference (content and style) to HDGANHDGAN · Oxford-102 64x64FID: 40.02 -> 37.94Improved
add dual adversarial inference to HDGANHDGAN · CUB 64x64FID: 20.60 -> 18.41Improved
add dual adversarial inference to HDGANHDGAN · COCO 64x64FID: 29.13 -> 27.07Improved
add dual adversarial inference to HDGANHDGAN · COCO 64x64Inception score: 8.64 -> 8.94Improved
add dual adversarial inference to HDGANHDGAN · CUB 64x64Inception score: 3.58 -> 3.58No clear effect
add dual adversarial inference to HDGANHDGAN · Oxford-102 64x64Inception score: 2.90 -> 2.90No clear effect
add dual adversarial inference to HDGANHDGAN · CUB 64x64Visual-semantic similarity: 0.263 -> 0.251No clear effect
add V_t2i matching-aware discriminator (ablation)Ours · CUB 64x64FID: 20.65 -> 18.41Improved
add V_t2i matching-aware discriminator (ablation)Ours · CUB 64x64Inception score: 3.31 -> 3.58Improved
add adversarial cycle-consistency V_cycle (ablation)Ours · CUB 64x64FID: 19.29 -> 18.41Improved
add adversarial cycle-consistency V_cycle (ablation)Ours · CUB 64x64Inception score: 3.53 -> 3.58Improved
use adversarial loss rather than l2 loss for cycle-consistency (ablation)Ours · CUB 64x64FID: 149.8 -> 18.41Improved

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