模拟人类记忆机制，让模型记住图像更像人。
Neural Encoding for Image Recall: Human-Like Memory
- 用噪声增强图像，模仿人类记忆的不确定性
- 自然图像召回准确率达97%，纹理图接近随机（52%）
- 适合研究类脑记忆与视觉认知的学者
在人工智能系统中实现类人记忆回溯仍是计算机视觉领域的挑战。人类能在单次曝光后回忆起图像，即使看过数千张图像，但面对随机纹理等非自然刺激时该能力显著下降。本文提出一种受人类记忆机制启发的方法，不存储原始像素数据，而是编码图像的高层语义信息。通过在编码前向图像添加噪声，引入类似人类记忆编码的非确定性特征。利用预训练模型的嵌入层，探究不同架构对图像编码的影响及其对记忆回溯的效果。实验显示，该方法在自然图像上达到97%的召回准确率，而在纹理图像上表现接近随机（52%）。研究揭示了编码过程的机制及其对机器学习记忆系统的意义，为类人智能记忆机制提供了新的理解。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。