An illustration of the Fashionpedia dataset and ontology

(a) main garment masks; (b) garment part masks; (c) both main garment and garment part masks; (d) fine-grained apparel attributes; (e) an exploded view of the annotation diagram: the image is annotated with both instance segmentation masks (white boxes) and per-mask fine-grained attributes (black boxes); (f) visualization of the Fashionpedia ontology: we created Fashionpedia ontology and separate the concept of categories (yellow nodes) and attributes (blue nodes) in fashion. It covers pre-defined garment categories used by both Deepfashion2 and ModaNet. Mapping with DeepFashion2 also shows the versatility of using attributes and categories. We are able to present all 13 garment classes in DeepFashion2 with 11 main garment categories, 1 garment part, and 7 attributes.

Tasks

Detection with localized attributes

Apparel object detection (bounding boxes or segmentation masks) with localized attributes prediction. One can also use the same set of annotation for apparel object detection task.

Annotation formats Evaluation Results formats

Attributes Classification

One can also merge attributes among all masks as global attributes and evaluate the attribute prediction.

Annotation formats

Download

Tools and model

Tools (Fashionpedia API) Baseline model

Data in JSON format

CVDF hosts the images and annotations in the Fashionpedia dataset.

Images Annotations

Data in csv format (Kaggle)

Annotations are in csv form at Kaggle platform

Kaggle site Images & Annotations