SKU-110K
Densely packed retail shelf images for detecting and counting products in challenging scenes.
What the resource contains
- Shelf images with closely spaced products
- Object bounding-box annotations
- Training and evaluation resources for dense detection
Potential uses
- Benchmark shelf-object detection
- Study overlapping detection errors
- Prototype retail item counting
Access & formats
Images / box annotations. External dependencies. Follow the project’s instructions on GitHub; some resources require external files, registration or approval.
License & reuse
The source explicitly restricts the dataset to academic and noncommercial use.
Important limitations
Retail shelf detection is adjacent to ecommerce. Object boxes do not provide a complete SKU-level product catalog.
Source & attribution
eg4000 — original GitHub project ↗
Documentation reviewed 2026-09-24. Review scope and licensing notes. Suggest a correction.
Related resources
Fashion-MNIST
zalandoresearch
A compact fashion-image classification benchmark suitable for learning and quick model comparisons.
IDX / image arrays · Repository / linked release
FEIDEGGER
zalandoresearch
Fashion photographs paired with multiple German descriptions for multimodal retrieval research.
Images / text annotations · Repository / linked release
DeepFashion2
switchablenorms
Clothing images with detailed annotations for detection, segmentation and consumer-to-shop retrieval.
Images / JSON annotations · External dependencies