arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.04360cs.CVcs.AIeess.IV
收藏

受连接性启发的上下文感知识别网络

Connectivity-Inspired Network for Context-Aware Recognition

National Research Council of Italy(意大利国家研究委员会);University of Pisa(比萨大学)

Gianluca Carloni, Sara Colantonio

AI总结:

该研究借鉴人类视觉皮层与皮层下连接机制,提出带双向调制的生物启发卷积网络及可即插即用的 Contextual Attention Block,用于建模物体共现和分层上下文,提升图像分类性能与类别激活解释稳健性。

摘要:

本文的目标有三个。我们通过广泛的文献综述向 AI 从业者介绍人类视觉系统;提出一种新颖的、受生物学启发的用于图像分类的神经网络;最后,展示一个新的即插即用模块,用于建模上下文感知。我们重点关注整合在生物大脑中发现的回路基序以解决视觉识别问题的效果。我们的卷积架构受到人类皮层和皮层下信息流连接性的启发,并实现了自下而上和自上而下的调制,以模拟视觉区与认知区之间广泛的传入和传出连接。我们的 Contextual Attention Block(上下文注意力块)简单且有效,可与任何前馈神经网络集成。它推断权重,并根据特征图对场景的因果影响将其与特征图相乘,从而建模图像中不同物体的共现关系。我们将该模块放置在不同的瓶颈处,以向模型注入分层的上下文感知能力。我们通过在基准数据上进行图像分类实验验证了所提方案,发现性能持续提升,并且通过类别激活生成的解释的稳健性也得到增强。我们的代码可在 https://github.com/gianlucarloni/CoCoReco 获取。

英文摘要:

The aim of this paper is threefold. We inform the AI practitioner about the human visual system with an extensive literature review; we propose a novel biologically motivated neural network for image classification; and, finally, we present a new plug-and-play module to model context awareness. We focus on the effect of incorporating circuit motifs found in biological brains to address visual recognition. Our convolutional architecture is inspired by the connectivity of human cortical and subcortical streams, and we implement bottom-up and top-down modulations that mimic the extensive afferent and efferent connections between visual and cognitive areas. Our Contextual Attention Block is simple and effective and can be integrated with any feed-forward neural network. It infers weights that multiply the feature maps according to their causal influence on the scene, modeling the co-occurrence of different objects in the image. We place our module at different bottlenecks to infuse a hierarchical context awareness into the model. We validated our proposals through image classification experiments on benchmark data and found a consistent improvement in performance and the robustness of the produced explanations via class activation. Our code is available at https://github.com/gianlucarloni/CoCoReco.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑