Neural Encoding for Image Recall: Human-Like Memory

TL;DR

This paper introduces a human-inspired image encoding method that enhances artificial memory recall, achieving high accuracy on natural images and revealing insights into biological memory processes.

Contribution

The paper proposes a novel encoding approach using pre-trained models to mimic human memory, improving image recall in artificial systems especially for natural images.

Findings

97% accuracy on natural images

52% accuracy on textures

Insights into encoding processes

Abstract

Achieving human-like memory recall in artificial systems remains a challenging frontier in computer vision. Humans demonstrate remarkable ability to recall images after a single exposure, even after being shown thousands of images. However, this capacity diminishes significantly when confronted with non-natural stimuli such as random textures. In this paper, we present a method inspired by human memory processes to bridge this gap between artificial and biological memory systems. Our approach focuses on encoding images to mimic the high-level information retained by the human brain, rather than storing raw pixel data. By adding noise to images before encoding, we introduce variability akin to the non-deterministic nature of human memory encoding. Leveraging pre-trained models' embedding layers, we explore how different architectures encode images and their impact on memory recall. Our method achieves impressive results, with 97% accuracy on natural images and near-random performance (52%) on textures. We provide insights into the encoding process and its implications for machine learning memory systems, shedding light on the parallels between human and artificial intelligence memory mechanisms.