# FashionLens: Toward Versatile Fashion Image Retrieval via Task-Adaptive Learning

arXiv: https://arxiv.org/abs/2605.22552 · HTML: https://mlsanity.com/paper/2605.22552/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks](https://mlsanity.com/paper/2410.05160/) (2024)
- [UniIR: Training and Benchmarking Universal Multimodal Information Retrievers](https://mlsanity.com/paper/2311.17136/) (2023)
- [MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs](https://mlsanity.com/paper/2411.02571/) (2024)
- [Automatic Spatially-aware Fashion Concept Discovery](https://mlsanity.com/paper/1708.01311/) (2017)
- [DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images](https://mlsanity.com/paper/1901.07973/) (2019)
- [Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup](https://mlsanity.com/paper/2101.06983/) (2021)
- [VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents](https://mlsanity.com/paper/2507.04590/) (2025)
- [Dialog-based Interactive Image Retrieval](https://mlsanity.com/paper/1805.00145/) (2018)
- [Learning Fashion Compatibility with Bidirectional LSTMs](https://mlsanity.com/paper/1707.05691/) (2017)
- [Fashion-Gen: The Generative Fashion Dataset and Challenge](https://mlsanity.com/paper/1806.08317/) (2018)
- [FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval](https://mlsanity.com/paper/2005.09801/) (2020)
- [Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Network](https://mlsanity.com/paper/1505.07922/) (2015)
- [FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks](https://mlsanity.com/paper/2303.02483/) (2023)
- [Simple but Effective Raw-Data Level Multimodal Fusion for Composed Image Retrieval](https://mlsanity.com/paper/2404.15875/) (2024)
- [Neural Compatibility Modeling with Attentive Knowledge Distillation](https://mlsanity.com/paper/1805.00313/) (2018)
- [FashionSAP: Symbols and Attributes Prompt for Fine-grained Fashion Vision-Language Pre-training](https://mlsanity.com/paper/2304.05051/) (2023)
- [Feature Decomposition for Reducing Negative Transfer: A Novel Multi-task Learning Method for Recommender System](https://mlsanity.com/paper/2302.05031/) (2023)
- [Composite Sketch+Text Queries for Retrieving Objects with Elusive Names and Complex Interactions](https://mlsanity.com/paper/2502.08438/) (2025)
- [MovingFashion: a Benchmark for the Video-to-Shop Challenge](https://mlsanity.com/paper/2110.02627/) (2021)
- [A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillation](https://mlsanity.com/paper/2603.20648/) (2026)

## Built on by (most cited first, 1 of 1)

- [Diverse-Intent Multi-Turn Fashion Image Retrieval](https://mlsanity.com/paper/2607.20291/) (2026)

## Abstract (arXiv)

Fashion image retrieval is a cornerstone of modern e-commerce systems. A unified framework that supports diverse query formats and search intentions is highly desired in practice. However, existing approaches focus on narrow retrieval tasks and do not fully capture such diversity. Therefore, in this work, we aim to develop a unified framework capable of handling diverse realistic fashion retrieval scenarios, achieving truly versatile fashion image retrieval. To establish a data foundation, we first introduce U-FIRE, a comprehensive benchmark that consolidates fragmented fashion datasets into a unified collection, supplemented by two manually curated datasets for testing generalization. Building upon this, we propose FashionLens, a unified framework based on Multimodal Large Language Models. To handle divergent matching objectives, we design a Proposal-Guided Spherical Query Calibrator that dynamically shifts query representations into task-aligned metric spaces via adaptive spherical linear interpolation. Additionally, to mitigate the optimization imbalance caused by varying task complexities and data scales, we develop a Gradient-Guided Adaptive Sampling strategy that automatically re-weights tasks based on realtime learning difficulty and the data scale prior. Experiments on U-FIRE show that FashionLens achieves state-of-the-art performance across diverse retrieval scenarios and generalizes robustly to unseen tasks. The data and code are publicly released at https://github.com/haokunwen/FashionLens.