Controlling Structured Output Representations from Attributes using Conditional Generative Models

TL;DR

This paper adapts the Conditional Variational Auto-encoder (CVAE) framework for controlled image generation based on attributes, demonstrating improved attribute-specific sample generation on face and bird datasets.

Contribution

It extends the CVAE framework to enable attribute-controlled structured output generation, enhancing robustness and disentanglement in multimodal distributions.

Findings

Successful generation of attribute-specific faces and bird images

Improved sample diversity with weighted variational lower bound

Recreated and trained CVAE architecture on CelebA and CUB datasets

Abstract

Structured output representation is a generative task explored in computer vision that often times requires the mapping of low dimensional features to high dimensional structured outputs. Losses in complex spatial information in deterministic approaches such as Convolutional Neural Networks (CNN) lead to uncertainties and ambiguous structures within a single output representation. A probabilistic approach through deep Conditional Generative Models (CGM) is presented by Sohn et al. in which a particular model known as the Conditional Variational Auto-encoder (CVAE) is introduced and explored. While the original paper focuses on the task of image segmentation, this paper adopts the CVAE framework for the task of controlled output representation through attributes. This approach allows us to learn a disentangled multimodal prior distribution, resulting in more controlled and robust approach to sample generation. In this work we recreate the CVAE architecture and train it on images conditioned on various attributes obtained from two image datasets; the Large-scale CelebFaces Attributes (CelebA) dataset and the Caltech-UCSD Birds (CUB-200-2011) dataset. We attempt to generate new faces with distinct attributes such as hair color and glasses, as well as different bird species samples with various attributes. We further introduce strategies for improving generalized sample generation by applying a weighted term to the variational lower bound.