OmniFashion: Towards Generalist Fashion Intelligence via Multi-Task Vision-Language Learning

2026-03-03

AI Summary

Existing fashion intelligence systems struggle to establish a unified visual-semantic structure due to fragmented tasks and incomplete annotations, limiting their generalization and reasoning capabilities. To address this, this work introduces FashionX, a million-scale dataset with fine-grained annotations, and proposes OmniFashion, a unified vision-language framework that, for the first time, integrates diverse tasks—including retrieval, recommendation, recognition, and dialogue—into a consistent conversational paradigm to enable cross-task collaborative reasoning. Leveraging a hierarchical attribute annotation scheme from global to local, large-scale vision-language pretraining, and multi-task learning, OmniFashion achieves state-of-the-art performance across multiple benchmarks, significantly improving task accuracy and cross-task generalization, thereby advancing the development of general-purpose fashion intelligence.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Computer Vision: Language and Vision
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Fashion intelligence spans multiple tasks, i.e., retrieval, recommendation, recognition, and dialogue, yet remains hindered by fragmented supervision and incomplete fashion annotations. These limitations jointly restrict the formation of consistent visual-semantic structures, preventing recent vision-language models (VLMs) from serving as a generalist fashion brain that unifies understanding and reasoning across tasks. Therefore, we construct FashionX, a million-scale dataset that exhaustively annotates visible fashion items within an outfit and organizes attributes from global to part-level. Built upon this foundation, we propose OmniFashion, a unified vision-language framework that bridges diverse fashion tasks under a unified fashion dialogue paradigm, enabling both multi-task reasoning and interactive dialogue. Experiments on multi-subtasks and retrieval benchmarks show that OmniFashion achieves strong task-level accuracy and cross-task generalization, highlighting its offering of a scalable path toward universal, dialogue-oriented fashion intelligence.

Problem

• fashion intelligence
• vision-language models
• multi-task learning
• incomplete annotations
• fragmented supervision

Innovation

• vision-language learning
• multi-task learning
• fashion intelligence
• dialogue-based reasoning
• fine-grained annotation