Datasets › COCO-MIG
COCO-MIG (COCO-MIG benchmark)
The COCO-MIG benchmark (Common Objects in Context Multi-Instance Generation) is a benchmark used to evaluate the generation capability of generators on text containing multiple attributes of multi-instance objects. This benchmark consists of 800 sets of examples sampled from the COCO dataset. Following the layout of the COCO dataset, each instance is assigned random color information, and corresponding global image descriptions are constructed according to templates. The COCO-MIG also provides a complete pipeline for resampling and evaluating. For relevant tools and specific details, please refer to our project's homepage.
Benchmarks archive 2025-07-28
All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Conditional Text-to-Image Synthesis | COCO-MIG | MIGC instance success rate 0.66 | MIGC: Multi-Instance Generation Controller for... | limuloo/migc | 5 | Compare |
Papers archive 2025-07-28
5 shown of 5 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 8. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis | 1 | 1 | 8 Feb 2024 | ran 8 of 9 samples (1 unverified; 9 pointer-only for licence) |
| InstanceDiffusion: Instance-level Control for Image Generation | 1 | 1 | 5 Feb 2024 | ran 17 of 18 samples (1 unverified) |
| BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion | 2 | 1 | 20 Jul 2023 | ran 4 of 5 samples (1 unverified; 5 pointer-only for licence) |
| GLIGEN: Open-Set Grounded Text-to-Image Generation | 1 | 1 | 17 Jan 2023 | ran 2 of 2 samples (0 unverified) |
| ReCo: Region-Controlled Text-to-Image Generation | 0 | 1 | 23 Nov 2022 | not harvested |
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
Variants archive 2025-07-28
- COCO-MIG
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections