From Zero-Shot to Few-Shot Learning: A Step of Embedding-Aware Generative Models

by   Liangjun Feng, et al.

Embedding-aware generative model (EAGM) addresses the data insufficiency problem for zero-shot learning (ZSL) by constructing a generator between semantic and visual embedding spaces. Thanks to the predefined benchmark and protocols, the number of proposed EAGMs for ZSL is increasing rapidly. We argue that it is time to take a step back and reconsider the embedding-aware generative paradigm. The purpose of this paper is three-fold. First, given the fact that the current embedding features in benchmark datasets are somehow out-of-date, we improve the performance of EAGMs for ZSL remarkably with embarrassedly simple modifications on the embedding features. This is an important contribution, since the results reveal that the embedding of EAGMs deserves more attention. Second, we compare and analyze a significant number of EAGMs in depth. Based on five benchmark datasets, we update the state-of-the-art results for ZSL and give a strong baseline for few-shot learning (FSL), including the classic unseen-class few-shot learning (UFSL) and the more challenging seen-class few-shot learning (SFSL). Finally, a comprehensive generative model repository, namely, generative any-shot learning (GASL) repository, is provided, which contains the models, features, parameters, and settings of EAGMs for ZSL and FSL. Any results in this paper can be readily reproduced with only one command line based on GASL.


page 1

page 2

page 9

page 10

page 15

page 19


Zero-Shot Learning - The Good, the Bad and the Ugly

Due to the importance of zero-shot learning, the number of proposed appr...

Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly

Due to the importance of zero-shot learning, i.e. classifying images whe...

Bias-Eliminated Semantic Refinement for Any-Shot Learning

When training samples are scarce, the semantic embedding technique, ie, ...

tSF: Transformer-based Semantic Filter for Few-Shot Learning

Few-Shot Learning (FSL) alleviates the data shortage challenge via embed...

Discrete Few-Shot Learning for Pan Privacy

In this paper we present the first baseline results for the task of few-...

Geometric Generalization Based Zero-Shot Learning Dataset Infinite World: Simple Yet Powerful

Raven's Progressive Matrices are one of the widely used tests in evaluat...

Please sign up or login with your details

Forgot password? Click here to reset