Contrastive language and vision learning of general fashion concepts
read the original abstract
The steady rise of online shopping goes hand in hand with the development of increasingly complex ML and NLP models. While most use cases are cast as specialized supervised learning problems, we argue that practitioners would greatly benefit from more transferable representations of products. In this work, we build on recent developments in contrastive learning to train FashionCLIP, a CLIP-like model for the fashion industry. We showcase its capabilities for retrieval, classification and grounding, and release our model and code to the community.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Loom: Hybrid Retrieval-Scoring Outfit Recommendation with Semantic Material Compatibility and Occasion-Aware Embedding Priors
Loom combines slot-constrained embedding retrieval with multi-objective scoring and two new CLIP-based techniques to generate coherent outfits, achieving 3.3x higher scores and 42% fewer violations than random baselin...
-
Fashion Florence: Fine-Tuning Florence-2 for Structured Fashion Attribute Extraction
A LoRA-fine-tuned Florence-2 model extracts structured fashion attributes from images, achieving 94.6% category accuracy and 63.0% material accuracy on a held-out test set, outperforming GPT-4o-mini and Gemini 2.5 Fla...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.