Tunable Soft Equivariance with Guarantees
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910078986092544 |
|---|---|
| author | Rahman, Md Ashiqur Hao, Lim Jun Jiang, Jeremiah Lim, Teck-Yian Yeh, Raymond A. |
| author_facet | Rahman, Md Ashiqur Hao, Lim Jun Jiang, Jeremiah Lim, Teck-Yian Yeh, Raymond A. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_26657 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Tunable Soft Equivariance with Guarantees Rahman, Md Ashiqur Hao, Lim Jun Jiang, Jeremiah Lim, Teck-Yian Yeh, Raymond A. Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Tunable Soft Equivariance with Guarantees |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2603.26657 |