Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional Learning

TL;DR

This paper introduces a cooperative training framework combining a fast initializer and a slow energy-based solver for high-dimensional conditional distribution learning, improving tasks like image translation and recovery.

Contribution

It proposes a novel joint training method for an initializer and an energy-based solver, enhancing conditional generation with iterative refinement.

Findings

Effective on class-to-image and image translation tasks

Outperforms GAN-based methods in solution refinement

Provides a slow thinking process guided by learned objectives

Abstract

This paper studies the problem of learning the conditional distribution of a high-dimensional output given an input, where the output and input may belong to two different domains, e.g., the output is a photo image and the input is a sketch image. We solve this problem by cooperative training of a fast thinking initializer and slow thinking solver. The initializer generates the output directly by a non-linear transformation of the input as well as a noise vector that accounts for latent variability in the output. The slow thinking solver learns an objective function in the form of a conditional energy function, so that the output can be generated by optimizing the objective function, or more rigorously by sampling from the conditional energy-based model. We propose to learn the two models jointly, where the fast thinking initializer serves to initialize the sampling of the slow thinking solver, and the solver refines the initial output by an iterative algorithm. The solver learns from the difference between the refined output and the observed output, while the initializer learns from how the solver refines its initial output. We demonstrate the effectiveness of the proposed method on various conditional learning tasks, e.g., class-to-image generation, image-to-image translation, and image recovery. The advantage of our method over GAN-based methods is that our method is equipped with a slow thinking process that refines the solution guided by a learned objective function.