DeepFashion2

Clothing images with detailed annotations for detection, segmentation and consumer-to-shop retrieval.

What the resource contains

  • Shop and consumer images across 13 clothing categories
  • Bounding boxes, landmarks, masks and style information
  • Pair IDs that support matching clothing instances

Potential uses

  • Detect and segment clothing
  • Estimate clothing landmarks
  • Evaluate consumer-to-catalog retrieval

Access & formats

Images / JSON annotations. External dependencies. Follow the project’s instructions on GitHub; some resources require external files, registration or approval.

License & reuse

The reviewed README alone does not establish unrestricted commercial rights. Check dataset access conditions and publisher terms.

Important limitations

Construct retrieval pairs using the documented item/style rules. A shared image pair ID alone is not enough to define a positive match.

Source & attribution

switchablenorms — original GitHub project ↗

Documentation reviewed 2026-09-24. Review scope and licensing notes. Suggest a correction.

Related resources

Fashion & product vision

Fashion-MNIST

zalandoresearch

A compact fashion-image classification benchmark suitable for learning and quick model comparisons.

Open license stated

IDX / image arrays · Repository / linked release

Fashion & product vision

FEIDEGGER

zalandoresearch

Fashion photographs paired with multiple German descriptions for multimodal retrieval research.

Review required

Images / text annotations · Repository / linked release