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

• URL: http://arxiv.org/abs/2603.02658v1
• Date: Tue, 03 Mar 2026 06:48:27 GMT
• Title: OmniFashion: Towards Generalist Fashion Intelligence via Multi-Task Vision-Language Learning
• Abstract summary: We construct FashionX, a million-scale dataset that exhaustively annotates visible fashion items within an outfit.<n>We propose OmniFashion, a unified vision-language framework that bridges diverse fashion tasks under a unified fashion dialogue paradigm.<n>Experiments on multi-subtasks and retrieval benchmarks show that OmniFashion achieves strong task-level accuracy and cross-task generalization.
• Score: 39.27438949211405
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• FashionStylist: An Expert Knowledge-enhanced Multimodal Dataset for Fashion Understanding [14.029623403884179]
  We introduce FashionStylist, an expert-annotated benchmark for holistic and expert-level fashion understanding.<n>FashionStylist provides professionally grounded annotations at both the item and outfit levels.<n>It supports three representative tasks: outfit-to-item grounding, outfit completion, and outfit evaluation.
  arXiv  Detail & Related papers  (2026-04-10T12:03:55Z)
• Revisiting Multi-Task Visual Representation Learning [52.93947931352643]
  We introduce MTV, a principled multi-task visual pretraining framework.<n>We leverage high-capacity "expert" models to synthesize dense, structured pseudo-labels at scale.<n>Our results demonstrate that MTV achieves "best-of-both-worlds" performance.
  arXiv  Detail & Related papers  (2026-01-20T11:59:19Z)
• From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models [66.36007274540113]
  Multimodal Large Language Models (MLLMs) strive to achieve a profound, human-like understanding of and interaction with the physical world.<n>They often exhibit a shallow and incoherent integration when acquiring information (Perception) and conducting reasoning (Cognition)<n>This survey introduces a novel and unified analytical framework: From Perception to Cognition"
  arXiv  Detail & Related papers  (2025-09-29T18:25:40Z)
• UniMoCo: Unified Modality Completion for Robust Multi-Modal Embeddings [9.344107676552408]
  We propose UniMoCo, a vision-language model architecture designed for multi-modal embedding tasks.<n>We develop a specialized training strategy to align embeddings from both original and modality-completed inputs.<n>Experiments show that UniMoCo outperforms previous methods while demonstrating consistent robustness across diverse settings.
  arXiv  Detail & Related papers  (2025-05-17T03:53:11Z)
• UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation [29.489516715874306]
  We present UniFashion, a unified framework that simultaneously tackles the challenges of multimodal generation and retrieval tasks within the fashion domain. Our model significantly outperforms previous single-task state-of-the-art models across diverse fashion tasks.
  arXiv  Detail & Related papers  (2024-08-21T03:17:20Z)
• Foundational Models Defining a New Era in Vision: A Survey and Outlook [151.49434496615427]
  Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The models learned to bridge the gap between such modalities coupled with large-scale training data facilitate contextual reasoning, generalization, and prompt capabilities at test time. The output of such models can be modified through human-provided prompts without retraining, e.g., segmenting a particular object by providing a bounding box, having interactive dialogues by asking questions about an image or video scene or manipulating the robot's behavior through language instructions.
  arXiv  Detail & Related papers  (2023-07-25T17:59:18Z)
• FashionSAP: Symbols and Attributes Prompt for Fine-grained Fashion Vision-Language Pre-training [12.652002299515864]
  We propose a method for fine-grained fashion vision-language pre-training based on fashion Symbols and Attributes Prompt (FashionSAP) Firstly, we propose the fashion symbols, a novel abstract fashion concept layer, to represent different fashion items. Secondly, the attributes prompt method is proposed to make the model learn specific attributes of fashion items explicitly.
  arXiv  Detail & Related papers  (2023-04-11T08:20:17Z)
• Language Is Not All You Need: Aligning Perception with Language Models [110.51362453720458]
  We introduce Kosmos-1, a Multimodal Large Language Model (MLLM) that can perceive general modalities, learn in context, and follow instructions. We train Kosmos-1 from scratch on web-scale multimodal corpora, including arbitrarily interleaved text and images, image-caption pairs, and text data. Experimental results show that Kosmos-1 achieves impressive performance on (i) language understanding, generation, and even OCR-free NLP. We also show that MLLMs can benefit from cross-modal transfer, i.e., transfer knowledge from language to multimodal, and from multimodal to language
  arXiv  Detail & Related papers  (2023-02-27T18:55:27Z)
• FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning [66.38951790650887]
  Multimodal tasks in the fashion domain have significant potential for e-commerce. We propose a novel fashion-specific pre-training framework based on weakly-supervised triplets constructed from fashion image-text pairs. We show the triplet-based tasks are an effective addition to standard multimodal pre-training tasks.
  arXiv  Detail & Related papers  (2022-10-26T21:01:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.