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

05/20/2022
by   Victor Boutin, et al.
0

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.

READ FULL TEXT

page 5

page 6

page 19

page 20

page 24

page 27

page 29

page 31

research
03/16/2016

One-Shot Generalization in Deep Generative Models

Humans have an impressive ability to reason about new concepts and exper...
research
10/13/2020

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

Generative models are increasingly able to produce remarkably high quali...
research
12/03/2018

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

Recent advances in deep generative models have lead to remarkable progre...
research
11/08/2018

Bias and Generalization in Deep Generative Models: An Empirical Study

In high dimensional settings, density estimation algorithms rely crucial...
research
02/09/2023

Feature Likelihood Score: Evaluating Generalization of Generative Models Using Samples

Deep generative models have demonstrated the ability to generate complex...
research
11/25/2022

Expanding Small-Scale Datasets with Guided Imagination

The power of Deep Neural Networks (DNNs) depends heavily on the training...
research
08/14/2023

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