提升模型对局部尺度变化的适应能力，让物体大小变化时表现更稳定。
Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer
- 用深度均衡框架构建可微分的归一化模块，实现局部尺度等变性。
- 在ImageNet上使ViT、DeiT等主流模型的精度和尺度一致性同步提升。
- 可无缝嵌入现有网络，适合需鲁棒尺度感知的视觉任务应用。
尺度变化是计算机视觉中的基本挑战：同一类物体可能呈现不同尺寸，且其视觉大小还受相机距离影响。这些变化具有局部性，即同一图像中不同物体的尺度变化可能各异。为有效应对尺度变化，本文提出深度均衡归一化器（DEC），以增强模型的局部尺度等变性。DEC可轻松集成至现有网络架构中，并适用于预训练模型。值得注意的是，在ImageNet这一高难度基准测试中，DEC显著提升了四种主流预训练深度网络（ViT、DeiT、Swin、BEiT）的性能与局部尺度一致性。代码已开源于https://github.com/ashiq24/local-scale-equivariance。
原文摘要 · Abstract (English)
Scale variation is a fundamental challenge in computer vision. Objects of the same class can have different sizes, and their perceived size is further affected by the distance from the camera. These variations are local to the objects, i.e., different object sizes may change differently within the same image. To effectively handle scale variations, we present a deep equilibrium canonicalizer (DEC) to improve the local scale equivariance of a model. DEC can be easily incorporated into existing network architectures and can be adapted to a pre-trained model. Notably, we show that on the competitive ImageNet benchmark, DEC improves both model performance and local scale consistency across four popular pre-trained deep-nets, e.g., ViT, DeiT, Swin, and BEiT. Our code is available at https://github.com/ashiq24/local-scale-equivariance.
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。