AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Symmetrical Flow Matching: Unified Image Generation, Segmentation, and Classification with Score-Based Generative Models

Francisco Caetano, Christiaan Viviers, Peter H.N. de With, Fons van der Sommen

AAAI 2026 · Image generation › Autoregressive and latent generation · approach: Retrieval and matching with generative features · 6 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
increase inference steps from 1 to 25 for image synthesis (ablation)SymmFlow · CelebAMask-HQFID: 88.5 -> 11.9Improved
increase inference steps from 1 to 25 for image synthesis (ablation)SymmFlow · COCO-StuffFID: 102.6 -> 7.0Improved
increase classification steps from 1 to 25 (ablation)SymmFlow · CIFAR-10 classificationaccuracy (%): 88.2 -> 90.6Improved
increase segmentation steps from 2 to 25 on CelebAMask-HQ (ablation)SymmFlow · CelebAMask-HQ segmentationmIoU: 70.3 -> 69.3No clear effect
increase segmentation steps from 1 to 20 on COCO-Stuff (ablation)SymmFlow · COCO-Stuff segmentationmIoU: 29.3 -> 40.1Improved
increase reverse-flow integration steps in toy classification (ablation)SymmFlow MLP · Toy spiral datasetaccuracy (%): 100.0 -> 82.0Hurt
joint symmetric flow model instead of SemFlowSymmFlow · COCO-Stuff semantic image synthesisFID: 90.0 -> 7.0Improved
joint symmetric flow model instead of SemFlowSymmFlow · COCO-Stuff segmentationmIoU: 35.7 -> 39.6Improved
joint symmetric flow model instead of SemFlowSymmFlow · CelebAMask-HQ segmentationmIoU: 69.4 -> 69.3No clear effect
unified SymmFlow vs specialized segmentersSymmFlow · COCO-Stuff segmentationmIoU: 46.7 -> 39.6Hurt

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