A degree of image identification at sub-human scales could be possible with more advanced clusters

2023/08/09 by Y J Prateek, J, Prateek Y
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Image Processing Techniques and Applications #Machine Learning (cs.LG) #Remote-Sensing Image Classification

paper · pdf · doi:10.48550/arxiv.2308.05092

openalex publication_date 2023/08/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The purpose of the research is to determine if currently available self-supervised learning techniques can accomplish human level comprehension of visual images using the same degree and amount of sensory input that people acquire from. Initial research on this topic solely considered data volume scaling. Here, we scale both the volume of data and the quality of the image. This scaling experiment is a self-supervised learning method that may be done without any outside financing. We find that scaling up data volume and picture resolution at the same time enables human-level item detection performance at sub-human sizes.We run a scaling experiment with vision transformers trained on up to 200000 images up to 256 ppi.

Related

• Scaling may be all you need for achieving human-level object recognition capacity with human-like visual experience
• How much human-like visual experience do current self-supervised learning algorithms need in order to achieve human-level object recognition?
• Scaling and Benchmarking Self-Supervised Visual Representation Learning
• Scale-Aware Pre-Training for Human-Centric Visual Perception: Enabling Lightweight and Generalizable Models
• Robustness of Humans and Machines on Object Recognition with Extreme Image Transformations