Zero-Shot Learning

180 papers with code • 7 benchmarks • 14 datasets

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

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

Greatest papers with code

Improving zero-shot learning by mitigating the hubness problem

facebookresearch/MUSE 20 Dec 2014

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.

Image Retrieval Zero-Shot Learning

Prototypical Networks for Few-shot Learning

learnables/learn2learn NeurIPS 2017

We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class.

Few-Shot Image Classification General Classification +2

CPM: A Large-scale Generative Chinese Pre-trained Language Model

TsinghuaAI/CPM-Generate 1 Dec 2020

However, applying GPT-3 to address Chinese NLP tasks is still challenging, as the training corpus of GPT-3 is primarily English, and the parameters are not publicly available.

Language Modelling Zero-Shot Learning

Learning to Compare: Relation Network for Few-Shot Learning

floodsung/LearningToCompare_FSL CVPR 2018

Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network.

Few-Shot Image Classification Zero-Shot Learning

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).

Knowledge Graphs Zero-Shot Learning

Synthesized Classifiers for Zero-Shot Learning

JudyYe/zero-shot-gcn CVPR 2016

Given semantic descriptions of object classes, zero-shot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating them to the seen classes, from which labeled examples are provided.

Zero-Shot Learning

Zero-Shot Learning by Convex Combination of Semantic Embeddings

JudyYe/zero-shot-gcn 19 Dec 2013

In other cases the semantic embedding space is established by an independent natural language processing task, and then the image transformation into that space is learned in a second stage.

Zero-Shot Learning

Learning Deep Representations of Fine-grained Visual Descriptions

hanzhanggit/StackGAN-v2 CVPR 2016

State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information.

Image Retrieval Zero-Shot Learning

Cross-lingual Contextualized Topic Models with Zero-shot Learning

MilaNLProc/contextualized-topic-models EACL 2021

They all cover the same content, but the linguistic differences make it impossible to use traditional, bag-of-word-based topic models.

Topic Models Transfer Learning +2

Rethinking Knowledge Graph Propagation for Zero-Shot Learning

cyvius96/adgpm CVPR 2019

Graph convolutional neural networks have recently shown great potential for the task of zero-shot learning.

Zero-Shot Learning