Reflective Human-Machine Co-adaptation for Enhanced Text-to-Image Generation Dialogue System
This addresses the issue of unpredictable interaction costs for non-expert users in image generation systems, though it appears incremental as it builds on existing dialogue-based refinement approaches.
The paper tackles the problem of ambiguous user prompts in text-to-image generation by proposing a reflective human-machine co-adaptation strategy (RHM-CAS) to enhance user-friendliness, with experiments showing its effectiveness in aligning outcomes with user preferences.
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.