Reflective Human-Machine Co-adaptation for Enhanced Text-to-Image Generation Dialogue System

TL;DR

This paper introduces RHM-CAS, a reflective co-adaptation strategy for text-to-image systems that improves understanding and user interaction, leading to better image generation aligned with user preferences.

Contribution

The paper presents a novel reflective human-machine co-adaptation approach that enhances user interaction and image quality in text-to-image generation systems.

Findings

Effective refinement of images through language interaction

Improved alignment with user preferences

Demonstrated success across multiple tasks

Abstract

Today's image generation systems are capable of producing realistic and high-quality images. However, user prompts often contain ambiguities, making it difficult for these systems to interpret users' potential intentions. Consequently, machines need to interact with users multiple rounds to better understand users' intents. The unpredictable costs of using or learning image generation models through multiple feedback interactions hinder their widespread adoption and full performance potential, especially for non-expert users. In this research, we aim to enhance the user-friendliness of our image generation system. To achieve this, we propose a reflective human-machine co-adaptation strategy, named RHM-CAS. Externally, the Agent engages in meaningful language interactions with users to reflect on and refine the generated images. Internally, the Agent tries to optimize the policy based on user preferences, ensuring that the final outcomes closely align with user preferences. Various experiments on different tasks demonstrate the effectiveness of the proposed method.