Déjà View:一种面向视觉任务的工作记忆模型
Déjà View: A Shared Working-Memory Model for Visual Tasks
这篇论文做了一个能同时记住图像又能做分类和再认的统一模型,同一套参数靠提示切换任务。结论挺有意思:延迟不伤记忆,但干扰图像越多越容易误判。做视觉记忆或认知建模研究的同学可以看看。
arXiv 上发布的新论文 Déjà View 提出一个图像工作记忆模型,核心机制是动态神经活动与图像特征之间的临时关联相结合。模型在五个任务上训练,包括在干扰图像呈现时记住样本、对干扰图像分类、以及判断图像是新出现还是曾经出现过,同一个训练好的模型通过显式提示切换完成全部任务。
实验发现:延迟时间对样本记忆几乎无影响,但看到更多图像会导致更多虚报(false alarms);在样本记忆加分类的组合任务上,被提问次数越多,所有问题的正确率越下降,即便样本记忆本身依然稳健。模型在每种任务 40 个短试次内保持稳定表现。
这项工作展示了单一工作记忆系统如何被灵活复用于不同任务,其错误同时取决于之前的图像历史与任务要求,对理解视觉记忆的计算模型有参考价值。
Déjà View: A Shared Working-Memory Model for Visual Tasks
A working-memory model must remember stimuli and use its memory flexibly to perform different tasks. Here we introduce a model of working memory for images that combines dynamic activity with temporary associations between image features. We train the model on five tasks, including remembering a sample while other images are presented, categorizing distractor images while remembering the sample, and determining whether an image is new or has been presented before. The same trained model performs all tasks, guided by explicit cues about which response is required. We use this flexible memory model to ask how delay, distraction, and image history affect performance. Delays have little effect on sample-memory performance for the delays we tested, while seeing more images leads to more false alarms even when the target image appeared equally recently in all cases. On the sample-memory-plus-categorization task, the probability of correct responses on all questions decreases as more questions are asked, despite robust sample-memory performance. Finally, the model maintains stable performance across 40 brief trials of each task under the tested conditions. Together, these results demonstrate how a single working-memory system can be flexibly used to perform different tasks, and how its errors depend on both previous images and task demands.
本条情报归属 AITOP「论文」核心追踪栏目。涉及核心实体与技术议题包括:工作记忆、视觉模型、论文、计算神经科学,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.LG」(@Mranmay Shetty, Gabriel Kreiman),经 AITOP 多维评分管线结构化提炼。