通过权重投影实现可调节的软等变性，提升模型性能并控制误差。
Tunable Soft Equivariance with Guarantees
- 将模型权重投影到设计子空间，实现可控等变性。
- 在ImageNet上同时提升性能并降低等变误差。
- 适用于ViT、ResNet等多种预训练模型，通用性强。
等变性是计算机视觉模型的重要性质，但真实数据中严格等变性难以满足，限制了模型性能。因此，控制等变程度具有重要意义。本文提出一种通用框架，通过将模型权重投影至设计子空间来构建软等变模型，适用于任意预训练架构，并提供诱导等变误差的理论界。实验证明，该方法在多个预训练主干网络（如ViT和ResNet）上对图像分类、语义分割及人体轨迹预测任务均有效。尤其在竞争性ImageNet基准上，模型性能提升的同时，等变误差显著降低。
原文摘要 · Abstract (English)
Equivariance is a fundamental property in computer vision models, yet strict equivariance is rarely satisfied in real-world data, which can limit a model's performance. Controlling the degree of equivariance is therefore desirable. We propose a general framework for constructing soft equivariant models by projecting the model weights into a designed subspace. The method applies to any pre-trained architecture and provides theoretical bounds on the induced equivariance error. Empirically, we demonstrate the effectiveness of our method on multiple pre-trained backbones, including ViT and ResNet, across image classification, semantic segmentation, and human-trajectory prediction tasks. Notably, our approach improves the performance while simultaneously reducing equivariance error on the competitive ImageNet benchmark.
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。