Multi-label zero-shot learning
12 papers with code • 3 benchmarks • 2 datasets
The goal of multi-label classification task is to predict a set of labels in an image. As an extension of zero-shot learning (ZSL), multi-label zero-shot learning (ML-ZSL) is developed to identify multiple seen and unseen labels in an image.
Benchmarks
These leaderboards are used to track progress in Multi-label zero-shot learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
NUS-WIDE
Open Images V4
Most implemented papers
ML-Decoder: Scalable and Versatile Classification Head
In this paper, we introduce ML-Decoder, a new attention-based classification head.
Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer
sunanhe/mkt
•
•
Specifically, our method exploits multi-modal knowledge of image-text pairs based on a vision and language pre-training (VLP) model.
