AI Paper Atlas

Research map / Image generation / Editing and style transfer

Unpaired Image Translation via Vector Symbolic Architectures

Justin Theiss, Jay Leverett, Daeil Kim, Aayush Prakash

ECCV 2022 · Image generation › Editing and style transfer · approach: Image-to-image translation

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 VSA-based cyclic loss (ablation)VSAIT · GTA to CityscapesmIoU: 10.21 -> 30.89Improved
learn the hypervector mapping with F instead of random mapping (ablation)VSAIT · GTA to CityscapesmIoU: 17.53 -> 30.89Improved
use hypervector dimension 4096 instead of 128 (ablation)VSAIT · GTA to CityscapesmIoU: 25.04 -> 30.89Improved
use hypervector dimension 2048 instead of 512 (ablation)VSAIT · GTA to CityscapesmIoU: 29.35 -> 30.87Improved
increase VSA loss weight lambda from 1 to 10 (ablation)VSAIT · GTA to CityscapesmIoU: 21.55 -> 30.89Improved
increase VSA loss weight lambda from 2 to 10 (ablation)VSAIT · GTA to CityscapesmIoU: 26.49 -> 30.89Improved
increase lambda from 10 to 20 (ablation)VSAIT · GTA to CityscapesmIoU: 30.89 -> 29.78Hurt
patch size 32 instead of 16 for feature extraction (ablation)VSAIT · GTA to CityscapesmIoU: 30.89 -> 32.29Mixed
patch size 8 instead of 16 for feature extraction (ablation)VSAIT · GTA to CityscapesmIoU: 30.89 -> 31.47No clear effect
VSAIT versus best baseline SRUNIT on segmentationVSAIT · GTA to CityscapesmIoU: 22.69 -> 30.89Improved
VSAIT versus EPE on KIDVSAIT · GTA to CityscapesKID: 10.95 -> 8.74Improved
VSAIT versus SRUNIT on pixel accuracy delta1 in photo to mapVSAIT · Aerial Photo to Google Mappixel accuracy delta1: 17.67 -> 15.2Hurt

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