FashionStylist: An Expert Knowledge-enhanced Multimodal Dataset for Fashion Understanding

TL;DR

FashionStylist introduces a comprehensive, expert-annotated dataset for holistic fashion understanding, enabling multiple tasks like grounding, completion, and evaluation to advance AI in fashion analysis.

Contribution

It provides a new expert-annotated benchmark supporting multiple fashion understanding tasks, addressing limitations of existing fragmented datasets.

Findings

FashionStylist improves outfit grounding and completion accuracy.

The dataset enhances MLLM-based fashion system performance.

Expert annotations enable more nuanced fashion reasoning.

Abstract

Fashion understanding requires both visual perception and expert-level reasoning about style, occasion, compatibility, and outfit rationale. However, existing fashion datasets remain fragmented and task-specific, often focusing on item attributes, outfit co-occurrence, or weak textual supervision, and thus provide limited support for holistic outfit understanding. In this paper, we introduce FashionStylist, an expert-annotated benchmark for holistic and expert-level fashion understanding. Constructed through a dedicated fashion-expert annotation pipeline, FashionStylist provides professionally grounded annotations at both the item and outfit levels. It supports three representative tasks: outfit-to-item grounding, outfit completion, and outfit evaluation. These tasks cover realistic item recovery from complex outfits with layering and accessories, compatibility-aware composition beyond co-occurrence matching, and expert-level assessment of style, season, occasion, and overall coherence. Experimental results show that FashionStylist serves not only as a unified benchmark for multiple fashion tasks, but also as an effective training resource for improving grounding, completion, and outfit-level semantic evaluation in MLLM-based fashion systems.