SuperFashion introduces superpixel tokens in a Transformer with attribute-guided attention for ASFR, reporting relative MAP gains of 1.84%, 9.27%, and 9.35% on FashionAI, DARN, and DeepFashion.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Patches: Superpixel Token-based Transformers for Attribute-Specific Fashion Retrieval
SuperFashion introduces superpixel tokens in a Transformer with attribute-guided attention for ASFR, reporting relative MAP gains of 1.84%, 9.27%, and 9.35% on FashionAI, DARN, and DeepFashion.