ResNet18通过残差流实现尺度不变性，关键在通道间信息融合。
Naturally Computed Scale Invariance in the Residual Stream of ResNet18
- 利用残差流中尺度等变表示的逐元素相加，实现尺度不变性计算。
- 中间层多个卷积通道表现出显著尺度不变性，且与识别性能相关。
- 为理解深层网络如何自动获得尺度鲁棒性提供了新机制，适合模型解释研究者参考。
视觉物体识别的关键能力之一是对图像变换变量（如光照、旋转、尺度）保持不变性。神经网络如何实现这一能力？以往机制可解释性研究揭示了InceptionV1中部分构建不变性的回路，但结果有限，且不同架构尚未深入探索。本文聚焦于缺乏残差结构的InceptionV1所不具备的ResNet18，特别关注其残差流。我们发现，中间块中的多个卷积通道表现出尺度不变性，该性质由块输入的小尺度副本与块前求和输出的大尺度副本进行逐元素残差相加所计算得出。通过后续消融实验，我们尝试将这些神经属性与尺度鲁棒的物体识别行为建立因果联系。初步结果表明，残差流可能通过这种机制实现尺度不变性，并影响最终行为。代码已公开：https://github.com/cest-andre/residual-stream-interp
原文摘要 · Abstract (English)
An important capacity in visual object recognition is invariance to image-altering variables which leave the identity of objects unchanged, such as lighting, rotation, and scale. How do neural networks achieve this? Prior mechanistic interpretability research has illuminated some invariance-building circuitry in InceptionV1, but the results are limited and networks with different architectures have remained largely unexplored. This work investigates ResNet18 with a particular focus on its residual stream, an architectural component which InceptionV1 lacks. We observe that many convolutional channels in intermediate blocks exhibit scale invariant properties, computed by the element-wise residual summation of scale equivariant representations: the block input's smaller-scale copy with the block pre-sum output's larger-scale copy. Through subsequent ablation experiments, we attempt to causally link these neural properties with scale-robust object recognition behavior. Our tentative findings suggest how the residual stream computes scale invariance and its possible role in behavior. Code is available at: https://github.com/cest-andre/residual-stream-interp
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。