Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2408.12454 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913648845258752 |
|---|---|
| author | Wu, Zhiqiang Liu, Yingjie Sun, Licheng Yang, Jian Dong, Hanlin Lin, Shing-Ho J. Tang, Xuan Mi, Jinpeng Jin, Bo Wei, Xian |
| author_facet | Wu, Zhiqiang Liu, Yingjie Sun, Licheng Yang, Jian Dong, Hanlin Lin, Shing-Ho J. Tang, Xuan Mi, Jinpeng Jin, Bo Wei, Xian |
| contents | Group Equivariant Convolution (GConv) can capture rotational equivariance from original data. It assumes uniform and strict rotational equivariance across all features as the transformations under the specific group. However, the presentation or distribution of real-world data rarely conforms to strict rotational equivariance, commonly referred to as Rotational Symmetry-Breaking (RSB) in the system or dataset, making GConv unable to adapt effectively to this phenomenon. Motivated by this, we propose a simple but highly effective method to address this problem, which utilizes a set of learnable biases called $G$-Biases under the group order to break strict group constraints and then achieve a Relaxed Rotational Equivariant Convolution (RREConv). To validate the efficiency of RREConv, we conduct extensive ablation experiments on the discrete rotational group $\mathcal{C}_n$. Experiments demonstrate that the proposed RREConv-based methods achieve excellent performance compared to existing GConv-based methods in both classification and 2D object detection tasks on the natural image datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12454 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Relaxed Rotational Equivariance via $G$-Biases in Vision Wu, Zhiqiang Liu, Yingjie Sun, Licheng Yang, Jian Dong, Hanlin Lin, Shing-Ho J. Tang, Xuan Mi, Jinpeng Jin, Bo Wei, Xian Computer Vision and Pattern Recognition Artificial Intelligence Group Equivariant Convolution (GConv) can capture rotational equivariance from original data. It assumes uniform and strict rotational equivariance across all features as the transformations under the specific group. However, the presentation or distribution of real-world data rarely conforms to strict rotational equivariance, commonly referred to as Rotational Symmetry-Breaking (RSB) in the system or dataset, making GConv unable to adapt effectively to this phenomenon. Motivated by this, we propose a simple but highly effective method to address this problem, which utilizes a set of learnable biases called $G$-Biases under the group order to break strict group constraints and then achieve a Relaxed Rotational Equivariant Convolution (RREConv). To validate the efficiency of RREConv, we conduct extensive ablation experiments on the discrete rotational group $\mathcal{C}_n$. Experiments demonstrate that the proposed RREConv-based methods achieve excellent performance compared to existing GConv-based methods in both classification and 2D object detection tasks on the natural image datasets. |
| title | Relaxed Rotational Equivariance via $G$-Biases in Vision |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2408.12454 |