{"title":"图像再现的神经编码:类人记忆","authors":"Virgile Foussereau, Robin Dumas","doi":"arxiv-2409.11750","DOIUrl":null,"url":null,"abstract":"Achieving human-like memory recall in artificial systems remains a\nchallenging frontier in computer vision. Humans demonstrate remarkable ability\nto recall images after a single exposure, even after being shown thousands of\nimages. However, this capacity diminishes significantly when confronted with\nnon-natural stimuli such as random textures. In this paper, we present a method\ninspired by human memory processes to bridge this gap between artificial and\nbiological memory systems. Our approach focuses on encoding images to mimic the\nhigh-level information retained by the human brain, rather than storing raw\npixel data. By adding noise to images before encoding, we introduce variability\nakin to the non-deterministic nature of human memory encoding. Leveraging\npre-trained models' embedding layers, we explore how different architectures\nencode images and their impact on memory recall. Our method achieves impressive\nresults, with 97% accuracy on natural images and near-random performance (52%)\non textures. We provide insights into the encoding process and its implications\nfor machine learning memory systems, shedding light on the parallels between\nhuman and artificial intelligence memory mechanisms.","PeriodicalId":501130,"journal":{"name":"arXiv - CS - Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Neural Encoding for Image Recall: Human-Like Memory\",\"authors\":\"Virgile Foussereau, Robin Dumas\",\"doi\":\"arxiv-2409.11750\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Achieving human-like memory recall in artificial systems remains a\\nchallenging frontier in computer vision. Humans demonstrate remarkable ability\\nto recall images after a single exposure, even after being shown thousands of\\nimages. However, this capacity diminishes significantly when confronted with\\nnon-natural stimuli such as random textures. In this paper, we present a method\\ninspired by human memory processes to bridge this gap between artificial and\\nbiological memory systems. Our approach focuses on encoding images to mimic the\\nhigh-level information retained by the human brain, rather than storing raw\\npixel data. By adding noise to images before encoding, we introduce variability\\nakin to the non-deterministic nature of human memory encoding. Leveraging\\npre-trained models' embedding layers, we explore how different architectures\\nencode images and their impact on memory recall. Our method achieves impressive\\nresults, with 97% accuracy on natural images and near-random performance (52%)\\non textures. We provide insights into the encoding process and its implications\\nfor machine learning memory systems, shedding light on the parallels between\\nhuman and artificial intelligence memory mechanisms.\",\"PeriodicalId\":501130,\"journal\":{\"name\":\"arXiv - CS - Computer Vision and Pattern Recognition\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computer Vision and Pattern Recognition\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11750\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11750","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Neural Encoding for Image Recall: Human-Like Memory
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.