Out-of-distribution (OOD) detection empowers the model trained on the closed image set to identify unknown data in the open world. Though many prior techniques have yielded considerable improvements in this research direction, two crucial obstacles still remain. Firstly, a unified perspective has yet to be presented to view the developed arts with individual designs, which is vital for providing insights into future work. Secondly, we expect sufficient natural OOD supervision to promote the generation of compact boundaries between the in-distribution (ID) and OOD data without collecting explicit OOD samples. To tackle these issues, we propose a general probabilistic framework to interpret many existing methods and an OOD-data-free model, namely \textbf{S}elf-supervised \textbf{S}ampling for \textbf{O}OD \textbf{D}etection (SSOD). SSOD efficiently exploits natural OOD signals from the ID data based on the local property of convolution. With these supervisions, it jointly optimizes the OOD detection and conventional ID classification in an end-to-end manner. Extensive experiments reveal that SSOD establishes competitive state-of-the-art performance on many large-scale benchmarks, outperforming the best previous method by a large margin, \eg, reporting \textbf{-6.28\%} FPR95 and \textbf{+0.77\%} AUROC on ImageNet, \textbf{-19.01\%} FPR95 and \textbf{+3.04\%} AUROC on CIFAR-10, and top-ranked performance on hard OOD datasets, \ie, ImageNet-O and OpenImage-O.

翻译：分布外（OOD）检测使基于封闭图像集训练的模型能够在开放世界中识别未知数据。尽管先前众多技术在此研究方向取得了显著进展，但仍存在两个关键障碍。首先，尚未形成统一视角来审视具有个性化设计的现有方法，而这对于未来研究提供洞见至关重要。其次，我们期望在不收集显式OOD样本的情况下，通过充足的天然OOD监督来促进分布内（ID）与OOD数据之间紧凑边界的生成。为解决这些问题，我们提出一种通用的概率框架来解释现有多种方法，并设计了一种免OOD数据的模型——即**自监督采样**的**OOD**检测（SSOD）。SSOD基于卷积的局部特性，高效利用ID数据中的天然OOD信号。通过这类监督信息，它以端到端方式联合优化OOD检测与常规ID分类。大量实验表明，SSOD在多个大规模基准测试中建立了具有竞争力的最先进性能，大幅超越此前最优方法，例如在ImageNet上实现**-6.28%**的FPR95和**+0.77%**的AUROC，在CIFAR-10上实现**-19.01%**的FPR95和**+3.04%**的AUROC，并在困难OOD数据集（即ImageNet-O和OpenImage-O）上取得顶尖性能。