Diversity vs. Recognizability: Human-like generalization in one-shot generative models

by   Victor Boutin, et al.

Robust generalization to new concepts has long remained a distinctive feature of human intelligence. However, recent progress in deep generative models has now led to neural architectures capable of synthesizing novel instances of unknown visual concepts from a single training example. Yet, a more precise comparison between these models and humans is not possible because existing performance metrics for generative models (i.e., FID, IS, likelihood) are not appropriate for the one-shot generation scenario. Here, we propose a new framework to evaluate one-shot generative models along two axes: sample recognizability vs. diversity (i.e., intra-class variability). Using this framework, we perform a systematic evaluation of representative one-shot generative models on the Omniglot handwritten dataset. We first show that GAN-like and VAE-like models fall on opposite ends of the diversity-recognizability space. Extensive analyses of the effect of key model parameters further revealed that spatial attention and context integration have a linear contribution to the diversity-recognizability trade-off. In contrast, disentanglement transports the model along a parabolic curve that could be used to maximize recognizability. Using the diversity-recognizability framework, we were able to identify models and parameters that closely approximate human data.


page 5

page 6

page 19

page 20

page 24

page 27

page 29

page 31


One-Shot Generalization in Deep Generative Models

Humans have an impressive ability to reason about new concepts and exper...

Random Network Distillation as a Diversity Metric for Both Image and Text Generation

Generative models are increasingly able to produce remarkably high quali...

Towards Accurate Generative Models of Video: A New Metric & Challenges

Recent advances in deep generative models have lead to remarkable progre...

Bias and Generalization in Deep Generative Models: An Empirical Study

In high dimensional settings, density estimation algorithms rely crucial...

Feature Likelihood Score: Evaluating Generalization of Generative Models Using Samples

Deep generative models have demonstrated the ability to generate complex...

Expanding Small-Scale Datasets with Guided Imagination

The power of Deep Neural Networks (DNNs) depends heavily on the training...

Development and Evaluation of Three Chatbots for Postpartum Mood and Anxiety Disorders

In collaboration with Postpartum Support International (PSI), a non-prof...

Please sign up or login with your details

Forgot password? Click here to reset