Vision Encoder-Decoder Models for AI Coaching

TL;DR

This paper presents an integrated vision-encoder-decoder model for AI coaching that processes visual inputs directly to enable natural dialogue, simplifying architecture and improving user experience.

Contribution

The paper introduces a novel architecture combining Vision Transformer and GPT-2 for direct visual input processing in AI coaching, differing from traditional separate models.

Findings

Model effectively processes visual inputs for coaching dialogues.

Scalability demonstrated with different GPT-2 sizes.

Potential for versatile AI coaching applications.

Abstract

This research paper introduces an innovative AI coaching approach by integrating vision-encoder-decoder models. The feasibility of this method is demonstrated using a Vision Transformer as the encoder and GPT-2 as the decoder, achieving a seamless integration of visual input and textual interaction. Departing from conventional practices of employing distinct models for image recognition and text-based coaching, our integrated architecture directly processes input images, enabling natural question-and-answer dialogues with the AI coach. This unique strategy simplifies model architecture while enhancing the overall user experience in human-AI interactions. We showcase sample results to demonstrate the capability of the model. The results underscore the methodology's potential as a promising paradigm for creating efficient AI coach models in various domains involving visual inputs. Importantly, this potential holds true regardless of the particular visual encoder or text decoder chosen. Additionally, we conducted experiments with different sizes of GPT-2 to assess the impact on AI coach performance, providing valuable insights into the scalability and versatility of our proposed methodology.