tinyvision/SOLIDER

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1504 stars · 234 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

SOLIDER is a semantic-controllable self-supervised learning framework that learns general human representations from massive unlabeled human images. It provides pretrained backbones whose semantic/appearance information ratio can be tuned via a semantic controller to benefit downstream human-centric vision tasks.

Use cases

• pretrain a backbone for person re-identification
• improve pedestrian attribute recognition models
• boost pedestrian detection on CityPersons
• fine-tune features for human pose estimation on COCO
• transfer learning for human parsing and semantic segmentation
• person search in surveillance imagery

When to choose

• your downstream task is human-centric (re-ID, pose, pedestrian detection, person search)
• you lack labeled human images and want strong self-supervised pretrained features
• you need to control the semantic vs appearance trade-off in representations

When to avoid

• your task involves general objects rather than humans
• you need a lightweight model for edge devices
• you require actively maintained software with frequent updates

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision machine-learning deep-learning python self-supervised-learning human-centric pretrained-model cvpr2023 person-reidentification pedestrian-detection pose-estimation linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="tinyvision/SOLIDER")