mlsanityData to 7 Oct 2026

FashionSAP: Symbols and Attributes Prompt for Fine-grained Fashion Vision-Language Pre-training

arXiv 2304.05051 ↗First posted 11 Apr 2023cs.CV cs.CLcited by 14

On the map: Multimodal LLMs / vision-language models → Document understanding and multimodal RAG

Abstract (arXiv)

Fashion vision-language pre-training models have shown efficacy for a wide range of downstream tasks. However, general vision-language pre-training models pay less attention to fine-grained domain features, while these features are important in distinguishing the specific domain tasks from general tasks. We propose a method for fine-grained fashion vision-language pre-training based on fashion Symbols and Attributes Prompt (FashionSAP) to model fine-grained multi-modalities fashion attributes and characteristics. Firstly, we propose the fashion symbols, a novel abstract fashion concept layer, to represent different fashion items and to generalize various kinds of fine-grained fashion features, making modelling fine-grained attributes more effective. Secondly, the attributes prompt method is proposed to make the model learn specific attributes of fashion items explicitly. We design proper prompt templates according to the format of fashion data. Comprehensive experiments are conducted on two public fashion benchmarks, i.e., FashionGen and FashionIQ, and FashionSAP gets SOTA performances for four popular fashion tasks. The ablation study also shows the proposed abstract fashion symbols, and the attribute prompt method enables the model to acquire fine-grained semantics in the fashion domain effectively. The obvious performance gains from FashionSAP provide a new baseline for future fashion task research.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 37 of its 53 references that are in the map. First posted on arXiv 11 Apr 2023.

Builds on

37 of 53 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Kaleido-BERT: Vision-Language Pre-training on Fashion Domain30 Mar

Other references · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  8. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  9. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  10. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  11. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  12. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
24 more
  1. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  2. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
  3. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  4. 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,213
  5. 2019VL-BERT: Pre-training of Generic Visual-Linguistic Representationscited by 954
  6. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  7. 2021Multimodal Few-Shot Learning with Frozen Language Modelscited by 657
  8. 2021FILIP: Fine-grained Interactive Language-Image Pre-Trainingcited by 626
  9. 2021Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Modelscited by 244
  10. 2018Composing Text and Image for Image Retrieval - An Empirical Odysseycited by 234
  11. 2021Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learningcited by 187
  12. 2021CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Modelscited by 182
  13. 2021Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Modelscited by 139
  14. 2020ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Datacited by 136
  15. 2021Improving and Simplifying Pattern Exploiting Trainingcited by 97
  16. 2017Learning Fashion Compatibility with Bidirectional LSTMscited by 69
  17. 2018Fashion-Gen: The Generative Fashion Dataset and Challengecited by 65
  18. 2018Learning Type-Aware Embeddings for Fashion Compatibilitycited by 61
  19. 2020FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrievalcited by 55
  20. 2020Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewardscited by 37
  21. 2022FashionViL: Fashion-Focused Vision-and-Language Representation Learningcited by 32
  22. 2022CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrievalcited by 25
  23. 2021VLDeformer: Vision-Language Decomposed Transformer for Fast Cross-Modal Retrievalcited by 6
  24. 2022Prompt-based Text Entailment for Low-Resource Named Entity Recognitioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 7.

14 papers.

Sort:

By area:

  1. 2025OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrievalcited by 40
  2. 2026TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrievalcited by 13
  3. 2024Leveraging Large Language Models for Multimodal Searchcited by 11
  4. 2024SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretrainingcited by 8
  5. 2026ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrievalcited by 3
  6. 2025Color Me Correctly: Bridging Perceptual Color Spaces and Text Embeddings for Improved Diffusion Generationcited by 2
  7. 2024FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentationcited by 1
  8. 2024FashionFAE: Fine-grained Attributes Enhanced Fashion Vision-Language Pre-trainingcited by 1
  9. 2025PinLanding: Content-First Keyword Landing Page Generation via Multi-Modal AI for Web-Scale Discoverycited by 1
  10. 2026Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusioncited by 1
  11. 2026A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillationcited by 1
  12. 2026FashionLens: Toward Versatile Fashion Image Retrieval via Task-Adaptive Learningcited by 1
2 more
  1. 2026NaiLIA: Multimodal Nail Design Retrieval Based on Dense Intent Descriptions and Palette Queriescited by 0
  2. 2026Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AIcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Zero-Shot Product Attribute Labeling with Vision-Language Models: A Three-Tier Evaluation Framework
  2. 2026Fashion Florence: Fine-Tuning Florence-2 for Structured Fashion Attribute Extraction
  3. 2026FashionStylist: An Expert Knowledge-enhanced Multimodal Dataset for Fashion Understanding
  4. 2026OmniFashion: Towards Generalist Fashion Intelligence via Multi-Task Vision-Language Learning
  5. 2026Exploring Multi-Modal Large Language Models and Two-Stage Fine-Tuning for Fashion Image Retrieval
  6. 2026Grounding Free-Form Instructions for Fashion Complementary Image Generation
  7. 2026RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-Attributes
  8. 2025FashionM3: Multimodal, Multitask, and Multiround Fashion Assistant based on Unified Vision-Language Model