Research map / Detection and segmentation / Open-set and few-shot detection
Generating Multiple Objects at Spatially Distinct Locations
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add object pathways and layout encoding | StackGAN · MS-COCO | IS: 10.62 to 12.12 | Helped |
| Add object pathways and layout encoding | StackGAN · MS-COCO | FID: 74.05 to 55.30 | Helped |
| Add object pathways and layout encoding | AttnGAN · MS-COCO | IS: 23.61 to 24.76 | Helped |
| Add object pathways and layout encoding | AttnGAN · MS-COCO | FID: 33.10 to 33.35 | No clear effect |
| Remove the generator layout encoding (ablation) | Full model · Multi-MNIST | digit identity and location control | Hurt |
| Remove the discriminator object pathway (ablation) | Full model · Multi-MNIST | digit identity control | Hurt |
| Remove the generator object pathway (ablation) | Full model · Multi-MNIST | digit identity control | Hurt |
| Remove both generator and discriminator object pathways (ablation) | Full model · Multi-MNIST | location and identity control | Hurt |
| Disable the object pathway during generation (ablation) | StackGAN + Object Pathways · MS-COCO | object detail | Hurt |
| Disable the global pathway during generation (ablation) | StackGAN + Object Pathways · MS-COCO | background and global layout | Hurt |
Closest papers by meaning
- Exploiting Relationship for Complex-scene Image Generation (AAAI 2021 · similarity 0.91)
- Context-Aware Layout to Image Generation With Enhanced Object Appearance (CVPR 2021 · similarity 0.90)
- Object-Centric Image Generation from Layouts (AAAI 2021 · similarity 0.90)
- Learning What and Where to Draw (NeurIPS 2016 · similarity 0.88)
- Image Generation From Scene Graphs (CVPR 2018 · similarity 0.88)
- Unlocking Pre-trained Image Backbones for Semantic Image Synthesis (CVPR 2024 · similarity 0.86)
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.