About

( Image credit: Prototypical Networks for Few shot Learning in PyTorch )

You can view blog posts such as this to get a high-level understanding:

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Subtasks

Datasets

Latest papers with code

Dynamic VAEs with Generative Replay for Continual Zero-shot Learning

26 Apr 2021DVGR-CZSL/DVGR-CZSL

Continual zero-shot learning(CZSL) is a new domain to classify objects sequentially the model has not seen during training.

CONTINUAL LEARNING ZERO-SHOT LEARNING

4
26 Apr 2021

Revisiting Document Representations for Large-Scale Zero-Shot Learning

21 Apr 2021heendung/vs-zsl

Zero-shot learning aims to recognize unseen objects using their semantic representations.

ZERO-SHOT LEARNING

0
21 Apr 2021

Zero-Shot Learning on 3D Point Cloud Objects and Beyond

11 Apr 2021ali-chr/Transductive_ZSL_3D_Point_Cloud

Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification.

3D POINT CLOUD CLASSIFICATION CLASSIFICATION DOMAIN ADAPTATION IMAGE CLASSIFICATION POINT CLOUD CLASSIFICATION ZERO-SHOT LEARNING

10
11 Apr 2021

Contrastive Embedding for Generalized Zero-Shot Learning

30 Mar 2021Hanzy1996/CE-GZSL

To tackle this issue, we propose to integrate the generation model with the embedding model, yielding a hybrid GZSL framework.

GENERALIZED ZERO-SHOT LEARNING

18
30 Mar 2021

Incrementally Zero-Shot Detection by an Extreme Value Analyzer

23 Mar 2021KennithLi/Awesome-Zero-Shot-Object-Detection

However, zero-shot learning models assume that all seen classes should be known beforehand, while incremental learning models cannot recognize unseen classes.

CLASS-INCREMENTAL LEARNING INCREMENTAL LEARNING OBJECT DETECTION ZERO-SHOT LEARNING

3
23 Mar 2021

Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling

13 Mar 2021jitinkrishnan/Multilingual-ZeroShot-SlotFilling

Predicting user intent and detecting the corresponding slots from text are two key problems in Natural Language Understanding (NLU).

NATURAL LANGUAGE UNDERSTANDING SLOT FILLING ZERO-SHOT LEARNING

4
13 Mar 2021

Goal-Oriented Gaze Estimation for Zero-Shot Learning

5 Mar 2021osierboy/GEM-ZSL

Therefore, we introduce a novel goal-oriented gaze estimation module (GEM) to improve the discriminative attribute localization based on the class-level attributes for ZSL.

GAZE ESTIMATION GENERALIZED ZERO-SHOT LEARNING

16
05 Mar 2021

Counterfactual Zero-Shot and Open-Set Visual Recognition

1 Mar 2021yue-zhongqi/gcm-cf

We show that the key reason is that the generation is not Counterfactual Faithful, and thus we propose a faithful one, whose generation is from the sample-specific counterfactual question: What would the sample look like, if we set its class attribute to a certain class, while keeping its sample attribute unchanged?

OPEN SET LEARNING ZERO-SHOT LEARNING

70
01 Mar 2021

OntoZSL: Ontology-enhanced Zero-shot Learning

15 Feb 2021genggengcss/OntoZSL

The key of implementing ZSL is to leverage the prior knowledge of classes which builds the semantic relationship between classes and enables the transfer of the learned models (e. g., features) from training classes (i. e., seen classes) to unseen classes.

IMAGE CLASSIFICATION KNOWLEDGE GRAPH COMPLETION WORD EMBEDDINGS ZERO-SHOT LEARNING

4
15 Feb 2021