具有超丰富上下文的超高分辨率分割：一种新颖的基准
Ultra-High Resolution Segmentation with Ultra-Rich Context: A Novel Benchmark
AI总结：
为填补超高分辨率分割领域大规模基准的空白，本文提出了包含丰富上下文的URUR数据集，并设计了集成多级离散小波变换与平滑损失的WSDNet框架，在多个数据集上实现了最先进的分割性能。
摘要：
随着对超高分辨率（UHR）分割方法的兴趣日益浓厚和快速发展，迫切需要一个涵盖广泛场景并提供完整细粒度密集标注的大规模基准来推动该领域的发展。为此，我们引入了URUR数据集，即具有超丰富上下文的超高分辨率数据集。顾名思义，URUR包含大量分辨率足够高的图像（3,008张大小为5,120x5,120的图像）、广泛的复杂场景（来自63个城市）、足够丰富的上下文（包含8个类别的100万个实例）以及细粒度标注（约800亿个手动标注像素），这远优于包括DeepGlobe、Inria Aerial、UDD等在内的所有现有UHR数据集。此外，我们还提出了WSDNet，这是一个针对UHR分割，特别是具有超丰富上下文的情况，更加高效且有效的框架。具体而言，该框架自然地集成了多级离散小波变换（DWT）以减轻计算负担，同时保留更多空间细节，并引入了小波平滑损失（WSL），通过平滑约束来重建原始的结构化上下文和纹理。在多个UHR数据集上的实验证明了其最先进的性能。该数据集可在https://github.com/jankyee/URUR获取。
英文摘要：
With the increasing interest and rapid development of methods for Ultra-High Resolution (UHR) segmentation, a large-scale benchmark covering a wide range of scenes with full fine-grained dense annotations is urgently needed to facilitate the field. To this end, the URUR dataset is introduced, in the meaning of Ultra-High Resolution dataset with Ultra-Rich Context. As the name suggests, URUR contains amounts of images with high enough resolution (3,008 images of size 5,120x5,120), a wide range of complex scenes (from 63 cities), rich-enough context (1 million instances with 8 categories) and fine-grained annotations (about 80 billion manually annotated pixels), which is far superior to all the existing UHR datasets including DeepGlobe, Inria Aerial, UDD, etc.. Moreover, we also propose WSDNet, a more efficient and effective framework for UHR segmentation especially with ultra-rich context. Specifically, multi-level Discrete Wavelet Transform (DWT) is naturally integrated to release computation burden while preserve more spatial details, along with a Wavelet Smooth Loss (WSL) to reconstruct original structured context and texture with a smooth constrain. Experiments on several UHR datasets demonstrate its state-of-the-art performance. The dataset is available at https://github.com/jankyee/URUR.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
