<- Back to Datasets

Fashion IQ

Natural Language based Fashion Image Retrieval Dataset

Fashion IQ

We contribute a new dataset and a novel method for natural language based fashion image retrieval. Unlike previous fashion datasets, we provide natural language annotations to facilitate the training of interactive image retrieval systems, as well as the commonly used attribute based labels. We propose a novel approach and empirically demonstrate that combining natural language feedback with visual attribute information results in superior user feedback modeling and retrieval performance relative to using either of these modalities. We believe that our dataset can encourage further work on developing more natural and real-world applicable conversational shopping assistants.

View this Dataset
->
MIT-IBM Watson AI Lab
View author website
Task
Image Search / Retrieval
Annotation Types
Classification Tags
Items
Classes
Labels
Models using this dataset
Last updated on 
January 20, 2022
Licensed under 
Custom
Gain control of your training data
15,000+ ML engineers can’t be wrong