Zero-Shot Learning
561 papers with code • 18 benchmarks • 29 datasets
Zero-shot learning (ZSL) is a model's ability to detect classes never seen during training. The condition is that the classes are not known during supervised learning.
Earlier work in zero-shot learning use attributes in a two-step approach to infer unknown classes. In the computer vision context, more recent advances learn mappings from image feature space to semantic space. Other approaches learn non-linear multimodal embeddings. In the modern NLP context, language models can be evaluated on downstream tasks without fine tuning.
Benchmark datasets for zero-shot learning include aPY, AwA, and CUB, among others.
( Image credit: Prototypical Networks for Few shot Learning in PyTorch )
Further readings:
Benchmarks
These leaderboards are used to track progress in Zero-Shot Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Zero-Shot Learning models and implementations
CUB-200-2011
Oxford 102 Flower
PASCAL Context
AwA
SNIPS
AwA2
aPY
TVQA
LSMDC
MIT-States
Subtasks
Most implemented papers
Flamingo: a Visual Language Model for Few-Shot Learning
mlfoundations/open_flamingo
•
•
DeepMind 2022
Building models that can be rapidly adapted to novel tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research.
Improving zero-shot learning by mitigating the hubness problem
The zero-shot paradigm exploits vector-based word representations extracted from text corpora with unsupervised methods to learn general mapping functions from other feature spaces onto word space, where the words associated to the nearest neighbours of the mapped vectors are used as their linguistic labels.
Learning a Deep Embedding Model for Zero-Shot Learning
lzrobots/DeepEmbeddingModel_ZSL
•
•
CVPR 2017
In this paper we argue that the key to make deep ZSL models succeed is to choose the right embedding space.
Semantic Autoencoder for Zero-Shot Learning
We show that with this additional reconstruction constraint, the learned projection function from the seen classes is able to generalise better to the new unseen classes.
Feature Generating Networks for Zero-Shot Learning
akku1506/Feature-Generating-Networks-for-ZSL
•
•
CVPR 2018
Suffering from the extreme training data imbalance between seen and unseen classes, most of existing state-of-the-art approaches fail to achieve satisfactory results for the challenging generalized zero-shot learning task.
Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs
JudyYe/zero-shot-gcn
•
•
CVPR 2018
Given a learned knowledge graph (KG), our approach takes as input semantic embeddings for each node (representing visual category).
Rethinking Knowledge Graph Propagation for Zero-Shot Learning
Graph convolutional neural networks have recently shown great potential for the task of zero-shot learning.
Polarity Loss for Zero-shot Object Detection
This setting gives rise to the need for correct alignment between visual and semantic concepts, so that the unseen objects can be identified using only their semantic attributes.
75 Languages, 1 Model: Parsing Universal Dependencies Universally
hyperparticle/udify
•
•
IJCNLP 2019
We present UDify, a multilingual multi-task model capable of accurately predicting universal part-of-speech, morphological features, lemmas, and dependency trees simultaneously for all 124 Universal Dependencies treebanks across 75 languages.
Deep Learning Models for Multilingual Hate Speech Detection
Hate speech detection is a challenging problem with most of the datasets available in only one language: English.
