Hopit AI

The intelligence layer fashion commerce runs on. We build fashion-native retrieval and attribute extraction, and we measure both in public: full corpus, one harness, competitors included, losses shown.

Two benchmark suites

They answer different questions, so they are kept apart and never combined into a single score. Retrieval asks which product a shopper meant. Attribute extraction asks what a garment actually is. A system can be strong at one and weak at the other.

MODA: retrieval and search

Given a photo or a phrase, find the right product. Covers image-to-product similarity, text-to-product catalogue search, and street-photo to catalogue matching. Every cell is MAP@10 at full corpus under one evaluator, with competitor models run through identical preprocessing.

Benchmarks · Code

MODA_NER: attribute extraction

Turn a fashion image into structured product data: category, colour, fit, neckline, sleeve length, pattern, material. Four frozen tracks covering garment crops, catalogue images, applicability-aware full-body photos and product text. Predictions are hashed before labels open.

Benchmarks · Code

What each one measures

SuiteQuestionInputScored on
MODAWhich product did they mean?A photo, or a phraseMAP@10, full corpus, one evaluator
MODA_NER cropWhat is this garment?A cropped garment15 attribute fields
MODA_NER catalogWhat colour and fit?A catalogue product image10 fields including colour and fit
MODA_NER fullbodyIs the attribute even visible?A full-body photo18 fields with an explicit not-applicable class
MODA_NER textWhat do the words claim?Product title or description13 entity types

The method both suites share

Reproduce any number

Both suites ship the scorers, the prediction files, and their hashes. We do not redistribute third-party datasets: you obtain each corpus under its own terms, and the builders recreate the frozen split from record IDs and checksums. If a number here is wrong, it is meant to be provable from the artefacts rather than argued about.