Generalized Few-Shot Learning

7 papers with code • 3 benchmarks • 4 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions

Sha-Lab/FEAT CVPR 2020

Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes with limited labels.

Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders

edgarschnfld/CADA-VAE-PyTorch CVPR 2019

Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space.

Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning

Sha-Lab/CASTLE 7 Jun 2019

In this paper, we investigate the problem of generalized few-shot learning (GFSL) -- a model during the deployment is required to learn about tail categories with few shots and simultaneously classify the head classes.

From Generalized zero-shot learning to long-tail with class descriptors

dvirsamuel/DRAGON 5 Apr 2020

Real-world data is predominantly unbalanced and long-tailed, but deep models struggle to recognize rare classes in the presence of frequent classes.

Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection

nhhoang96/Semantic_Matching Findings of the Association for Computational Linguistics 2020

Although recent works demonstrate that multi-level matching plays an important role in transferring learned knowledge from seen training classes to novel testing classes, they rely on a static similarity measure and overly fine-grained matching components.

Better Generalized Few-Shot Learning Even Without Base Data

bigdata-inha/zero-base-gfsl 29 Nov 2022

In this paper, we overcome this limitation by proposing a simple yet effective normalization method that can effectively control both mean and variance of the weight distribution of novel classes without using any base samples and thereby achieve a satisfactory performance on both novel and base classes.