Zero-Shot Learning
564 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
Event Extraction by Answering (Almost) Natural Questions
The problem of event extraction requires detecting the event trigger and extracting its corresponding arguments.
Transforming task representations to perform novel tasks
lampinen/HoMM
•
•
We demonstrate the effectiveness of this framework across a wide variety of tasks and computational paradigms, ranging from regression to image classification and reinforcement learning.
Zero-Shot Learning with Common Sense Knowledge Graphs
Zero-shot learning relies on semantic class representations such as hand-engineered attributes or learned embeddings to predict classes without any labeled examples.
Class Normalization for (Continual)? Generalized Zero-Shot Learning
universome/czsl
•
•
Normalization techniques have proved to be a crucial ingredient of successful training in a traditional supervised learning regime.
AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data
stanford-oval/genie-toolkit
•
•
EMNLP 2020
To demonstrate the generality of AutoQA, we also apply it to the Overnight dataset.
Contrastive Embedding for Generalized Zero-Shot Learning
Hanzy1996/CE-GZSL
•
•
CVPR 2021
To tackle this issue, we propose to integrate the generation model with the embedding model, yielding a hybrid GZSL framework.
Visually Grounded Reasoning across Languages and Cultures
The design of widespread vision-and-language datasets and pre-trained encoders directly adopts, or draws inspiration from, the concepts and images of ImageNet.
Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
sense-gvt/declip
•
•
ICLR 2022
Recently, large-scale Contrastive Language-Image Pre-training (CLIP) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferability to downstream tasks.
YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
coqui-ai/TTS
•
•
YourTTS brings the power of a multilingual approach to the task of zero-shot multi-speaker TTS.
ZeroGen: Efficient Zero-shot Learning via Dataset Generation
HKUNLP/zerogen
•
•
There is a growing interest in dataset generation recently due to the superior generative capacity of large pre-trained language models (PLMs).
