DeepAI AI Chat
Log In Sign Up

Towards creativity characterization of generative models via group-based subset scanning

by   Celia Cintas, et al.

Deep generative models, such as Variational Autoencoders (VAEs), have been employed widely in computational creativity research. However, such models discourage out-of-distribution generation to avoid spurious sample generation, limiting their creativity. Thus, incorporating research on human creativity into generative deep learning techniques presents an opportunity to make their outputs more compelling and human-like. As we see the emergence of generative models directed to creativity research, a need for machine learning-based surrogate metrics to characterize creative output from these models is imperative. We propose group-based subset scanning to quantify, detect, and characterize creative processes by detecting a subset of anomalous node-activations in the hidden layers of generative models. Our experiments on original, typically decoded, and "creatively decoded" (Das et al 2020) image datasets reveal that the proposed subset scores distribution is more useful for detecting creative processes in the activation space rather than the pixel space. Further, we found that creative samples generate larger subsets of anomalies than normal or non-creative samples across datasets. The node activations highlighted during the creative decoding process are different from those responsible for normal sample generation.


page 1

page 2

page 3

page 4


Subset Scanning Over Neural Network Activations

This work views neural networks as data generating systems and applies a...

Disentangled Dynamic Graph Deep Generation

Deep generative models for graphs have exhibited promising performance i...

Self-adversarial Variational Autoencoder with Gaussian Anomaly Prior Distribution for Anomaly Detection

Recently, deep generative models have become increasingly popular in uns...

Data-Copying in Generative Models: A Formal Framework

There has been some recent interest in detecting and addressing memoriza...

Eval all, trust a few, do wrong to none: Comparing sentence generation models

In this paper, we study recent neural generative models for text generat...

Detecting Out-of-Context Image-Caption Pairs in News: A Counter-Intuitive Method

The growth of misinformation and re-contextualized media in social media...

Score-Based Generative Models Detect Manifolds

Score-based generative models (SGMs) need to approximate the scores ∇log...