用超像素网格结构加速图像分割，性能不降反升。
Superpixel Integrated Grids for Fast Image Segmentation
- 将超像素整合为规则网格结构，统一输入格式
- 在四个数据集上达到像素级精度，训练速度显著提升
- 适合需要高效推理的嵌入式视觉应用
超像素常用于图像简化以提升处理与存储效率。然而，其不规则空间分布迫使深度学习方法依赖特殊训练算法和架构，削弱了超像素初衷。本文提出新型超像素数据结构SIGRID（Superpixel-Integrated Grid），作为分割任务中全分辨率图像的替代方案。通过融合经典形状描述符，SIGRID同时编码超像素的颜色与形状信息，并大幅降低输入维度。我们在两个主流卷积分割架构下，于四个基准数据集上评估SIGRID。结果表明，尽管数据压缩明显，SIGRID不仅匹配甚至在部分情况下超越像素级表示性能，且显著加速模型训练。这证明了SIGRID在准确率与计算效率间取得良好平衡。
原文摘要 · Abstract (English)
Superpixels have long been used in image simplification to enable more efficient data processing and storage. However, despite their computational potential, their irregular spatial distribution has often forced deep learning approaches to rely on specialized training algorithms and architectures, undermining the original motivation for superpixelations. In this work, we introduce a new superpixel-based data structure, SIGRID (Superpixel-Integrated Grid), as an alternative to full-resolution images in segmentation tasks. By leveraging classical shape descriptors, SIGRID encodes both color and shape information of superpixels while substantially reducing input dimensionality. We evaluate SIGRIDs on four benchmark datasets using two popular convolutional segmentation architectures. Our results show that, despite compressing the original data, SIGRIDs not only match but in some cases surpass the performance of pixel-level representations, all while significantly accelerating model training. This demonstrates that SIGRIDs achieve a favorable balance between accuracy and computational efficiency.
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。