AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Learning Hierarchical Semantic Image Manipulation through Structured Representations

Seunghoon Hong, Xinchen Yan, Thomas S. Huang, Honglak Lee

NeurIPS 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 68 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 semantic layout conditioning to image-context-only generation (ablation)SingleStream-Image · Cityscapes validation, predicted layoutSegmentation accuracy: 59.6 -> 76.3Improved
Add image-context conditioning to layout-only generation (ablation)SingleStream-Layout · Cityscapes validation, predicted layoutSSIM: 0.268 -> 0.296Improved
Use separate image and layout encoding pathways instead of one concatenated pathway (ablation)Image generator · Cityscapes validation, predicted layoutHuman eval. preference: 29.9 -> 40.0Improved
Use separate image and layout encoding pathways instead of one concatenated pathway (ablation)Image generator · Cityscapes validation, predicted layoutSSIM: 0.296 -> 0.299Improved
Use predicted rather than ground-truth semantic layout (ablation)TwoStream image generator · Cityscapes validationPerceptual qualityHurt
Use predicted layout conditioning rather than image context alone (ablation)TwoStream-Pred · Cityscapes validationImage generation qualityImproved
Use hierarchical manipulation instead of copying and pasting training objectsImage manipulation · Cityscapes validation, AMT comparisonHuman preference: 76.33%Improved
Add segmentation layout as input to Context EncoderContext Encoder · Cityscapes validationSegmentation accuracy: 26.4 -> 35.7Improved

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