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

TL;DR

OmniFashion introduces a unified vision-language framework trained on a large, exhaustively annotated fashion dataset, enabling multi-task reasoning and dialogue to advance generalist fashion intelligence.

Contribution

The paper presents OmniFashion, a novel multi-task vision-language model for fashion that unifies diverse tasks and is trained on the new FashionX dataset with detailed annotations.

Findings

Achieves strong accuracy on multiple fashion tasks

Demonstrates effective cross-task generalization

Enables interactive fashion dialogue

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.