YOLOS-Fashion — Object Detection AI Model
Trained on Fashionpedia, this YOLOS spots 46 apparel categories — shirts, dresses, shoes, bags, hats, jewellery, glasses — and reports each with a box and a confidence. Built for catalogue tagging and outfit breakdowns.
What it does
YOLOS Fashion detects clothing and fashion detail in a photograph: 46 Fashionpedia categories, each returned with a box and a confidence score.
It covers the garments - shirts, dresses, shoes, bags, hats, jewellery, glasses - and the design details on them, which is where a general-purpose detector gives up. Out comes an annotated image alongside a text list of what was found.
When to use it
- Cataloguing product photographs for a shop automatically
- Identifying garment types: shirts, trousers, dresses, jackets
- Finding accessories - hats, scarves, belts, shoes, bags, gloves
- Design detail a general detector misses: pockets, buttons, collars
- Reading an outfit, item by item, from a single picture
Details
- CategoryObject Detection
- Year2020
- LicenseCC-BY-4.0
Compliance & Provenance
- ProviderOpen-source · Specialized
- EU AI Act RiskMinimal Risk
- Art. 50 TransparencyNot applicable
Inputs & Outputs
- ImageInputimage
Source image for fashion item detection
- ImageOutputimage
Detected objects are highlighted with bounding boxes
- TextOutputstring
Detected types of objects with confidence scores
Tags
Alternatives in Object Detection
- DETR
General object detection on 91 COCO classes (DETR).
- DETR (Face Detector)
Face detection (DETR ResNet-50 fine-tuned). Fast.
- DETR (License Plate Detector)
License-plate detection (DETR ResNet-50). Fast.
- RF-DETR Medium
Real-time object detection on 80 COCO classes (RF-DETR Medium).
- YOLO-S
Fast object detection, 91 COCO classes (YOLOS-Small).