Learning the Bitter Lesson: Empirical Evidence from 20 Years of CVPR Proceedings

TL;DR

This paper analyzes 20 years of CVPR research to evaluate how well the field aligns with the 'bitter lesson' principle, highlighting trends in general-purpose algorithms and computational resource use.

Contribution

It provides empirical evidence on the evolution of computer vision research over two decades using NLP techniques to assess alignment with the 'bitter lesson' principles.

Findings

Increased adoption of general-purpose learning algorithms

Growing utilization of computational resources

Shift towards more scalable and resource-intensive methods

Abstract

This study examines the alignment of \emph{Conference on Computer Vision and Pattern Recognition} (CVPR) research with the principles of the "bitter lesson" proposed by Rich Sutton. We analyze two decades of CVPR abstracts and titles using large language models (LLMs) to assess the field's embracement of these principles. Our methodology leverages state-of-the-art natural language processing techniques to systematically evaluate the evolution of research approaches in computer vision. The results reveal significant trends in the adoption of general-purpose learning algorithms and the utilization of increased computational resources. We discuss the implications of these findings for the future direction of computer vision research and its potential impact on broader artificial intelligence development. This work contributes to the ongoing dialogue about the most effective strategies for advancing machine learning and computer vision, offering insights that may guide future research priorities and methodologies in the field.