用神经网络模拟人类视觉注意力机制，发现其可自动生成空间与特征注意力。
A Neural Network Model of Spatial and Feature-Based Attention
- 双网络架构：一个处理任务，另一个通过上下文信息引导注意力。
- 训练后模型自发形成类人空间与特征注意力模式。
- 为研究人类认知提供可计算的神经网络新方法。
视觉注意力是与视觉和记忆紧密关联的机制，自上而下的信息通过注意力影响视觉处理。我们设计了一个受人类视觉注意力启发的神经网络模型。该模型包含两个网络：一个作为基础处理器执行简单任务，另一个处理上下文信息，并通过注意力机制引导前者以适应更复杂的任务。在训练模型并可视化学习到的注意力响应后，我们发现模型产生的注意力模式与人类的空间注意力和特征注意力高度对应。这一发现表明，计算机视觉中的注意力机制与人类视觉注意力具有相似性，为利用神经网络模型研究人类认知提供了有前景的方向。
原文摘要 · Abstract (English)
Visual attention is a mechanism closely intertwined with vision and memory. Top-down information influences visual processing through attention. We designed a neural network model inspired by aspects of human visual attention. This model consists of two networks: one serves as a basic processor performing a simple task, while the other processes contextual information and guides the first network through attention to adapt to more complex tasks. After training the model and visualizing the learned attention response, we discovered that the model's emergent attention patterns corresponded to spatial and feature-based attention. This similarity between human visual attention and attention in computer vision suggests a promising direction for studying human cognition using neural network models.
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。