AI Paper Atlas

Research map / Image generation / GANs

Instance-Wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation

Weilun Wang, Wengang Zhou, Jianmin Bao, Dong Chen, Houqiang Li

ICCV 2021 · Image generation › GANs · approach: GAN-based image manipulation · 101 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 negative generator with diversity loss (ablation)CUT-style contrastive translation · CityscapesFID: 49.7 -> 48.5Improved
add negative generator with diversity loss (ablation)CUT-style contrastive translation · Cat->DogFID: 110.9 -> 55.8Improved
add negative generator with diversity loss (ablation)CUT-style contrastive translation · Horse->ZebraFID: 59.6 -> 39.6Improved
add negative generator with diversity loss (ablation)CUT-style contrastive translation · CityscapespAcc: 71.9 -> 71.4Hurt
add diversity loss to negative generator (ablation)NEGCUT · CityscapesFID: 91.5 -> 48.5Improved
add diversity loss to negative generator (ablation)NEGCUT · Cat->DogFID: 83.0 -> 55.8Improved
add diversity loss to negative generator (ablation)NEGCUT · Horse->ZebraFID: 72.1 -> 39.6Improved
use 256 negatives instead of 64 (ablation)NEGCUT · Cat->DogFID: 59.3 -> 55.8Mixed
use 256 negatives instead of 128 (ablation)NEGCUT · Cat->DogFID: 86.9 -> 55.8Improved
use 256 negatives instead of 512 (ablation)NEGCUT · Cat->DogFID: 62.8 -> 55.8Improved
use 256 negatives instead of 512 (ablation)NEGCUT · Horse->ZebraFID: 44.0 -> 39.6Improved
replace random negatives with generated hard negativesCUT · CityscapesFID: 56.4 -> 48.5Improved

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