带保证的可调软等变
Tunable Soft Equivariance with Guarantees
把预训练骨干的权重投影到设计好的子空间即可获得可控强度的软等变，并给出等变误差的理论界，视觉研究者可直接把它当作一个免重训的后处理插件，在分类、分割、轨迹预测等任务上按需调节等变程度。
原文依据 We propose a general framework for constructing soft equivariant models by projecting the model weights into a designed subspace.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论等变性是计算机视觉模型的一项基本性质，然而严格等变性在真实数据中很少得到满足，这可能限制模型的性能。因此，控制等变程度是可取的。我们提出一个通用框架，通过将模型权重投影到设计好的子空间来构造软等变模型。该方法适用于任意预训练架构，并给出了所诱导等变误差的理论界。在实验上，我们在多个预训练骨干网络（包括 ViT 和 ResNet）上，跨图像分类、语义分割和人体轨迹预测任务验证了该方法的有效性。值得注意的是，在具有竞争力的 ImageNet 基准上，我们的方法在提升性能的同时降低了等变误差。
英文原文摘要 826 字符
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.