Square Superpixel Generation and Representation Learning via Granular Ball Computing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914434137456640 |
|---|---|
| author | Xia, Shuyin Yang, Meng Dai, Dawei Chen, Fan Zhao, Shilin Han, Junwei Gao, Xinbo Wang, Guoyin Lu, Wen |
| author_facet | Xia, Shuyin Yang, Meng Dai, Dawei Chen, Fan Zhao, Shilin Han, Junwei Gao, Xinbo Wang, Guoyin Lu, Wen |
| contents | Superpixels provide a compact region-based representation that preserves object boundaries and local structures, and have therefore been widely used in a variety of vision tasks to reduce computational cost. However, most existing superpixel algorithms produce irregularly shaped regions, which are not well aligned with regular operators such as convolutions. Consequently, superpixels are often treated as an offline preprocessing step, limiting parallel implementation and hindering end-to-end optimization within deep learning pipelines. Motivated by the adaptive representation and coverage property of granular-ball computing, we develop a square superpixel generation approach. Specifically, we approximate superpixels using multi-scale square blocks to avoid the computational and implementation difficulties induced by irregular shapes, enabling efficient parallel processing and learnable feature extraction. For each block, a purity score is computed based on pixel-intensity similarity, and high-quality blocks are selected accordingly. The resulting square superpixels can be readily integrated as graph nodes in graph neural networks (GNNs) or as tokens in Vision Transformers (ViTs), facilitating multi-scale information aggregation and structured visual representation. Experimental results on downstream tasks demonstrate consistent performance improvements, validating the effectiveness of the proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_29460 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Square Superpixel Generation and Representation Learning via Granular Ball Computing Xia, Shuyin Yang, Meng Dai, Dawei Chen, Fan Zhao, Shilin Han, Junwei Gao, Xinbo Wang, Guoyin Lu, Wen Computer Vision and Pattern Recognition Superpixels provide a compact region-based representation that preserves object boundaries and local structures, and have therefore been widely used in a variety of vision tasks to reduce computational cost. However, most existing superpixel algorithms produce irregularly shaped regions, which are not well aligned with regular operators such as convolutions. Consequently, superpixels are often treated as an offline preprocessing step, limiting parallel implementation and hindering end-to-end optimization within deep learning pipelines. Motivated by the adaptive representation and coverage property of granular-ball computing, we develop a square superpixel generation approach. Specifically, we approximate superpixels using multi-scale square blocks to avoid the computational and implementation difficulties induced by irregular shapes, enabling efficient parallel processing and learnable feature extraction. For each block, a purity score is computed based on pixel-intensity similarity, and high-quality blocks are selected accordingly. The resulting square superpixels can be readily integrated as graph nodes in graph neural networks (GNNs) or as tokens in Vision Transformers (ViTs), facilitating multi-scale information aggregation and structured visual representation. Experimental results on downstream tasks demonstrate consistent performance improvements, validating the effectiveness of the proposed method. |
| title | Square Superpixel Generation and Representation Learning via Granular Ball Computing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.29460 |