Out-of-distribution (OOD) detection and lossless compression constitute two problems that can be solved by the training of probabilistic models on a first dataset with subsequent likelihood evaluation on a second dataset, where data distributions differ. By defining the generalization of probabilistic models in terms of likelihood we show that, in the case of image models, the OOD generalization ability is dominated by local features. This motivates our proposal of a Local Autoregressive model that exclusively models local image features towards improving OOD performance. We apply the proposed model to OOD detection tasks and achieve state-of-the-art unsupervised OOD detection performance without the introduction of additional data. Additionally, we employ our model to build a new lossless image compressor: NeLLoC (Neural Local Lossless Compressor) and report state-of-the-art compression rates and model size.

翻译：对第一个数据集进行概率模型培训,随后对第二个数据集进行概率评估,然后对第二个数据集进行可能性评估,从而在数据分布不同的情况下对概率模型进行定义,从概率角度对概率模型进行一般化,我们表明,就图像模型而言,OOOD的概括化能力以当地特征为主。这促使我们提议一个本地自动递减模型,专门模拟当地图像特征,以改善OOD的性能。我们将拟议模型应用于OOOD的探测任务,并在不引入额外数据的情况下实现最先进的不受监督的OOOD探测性能。此外,我们利用我们的模型建立一个新的无损图像压缩器:NELLoC(Neural Conness Connessor-NellooC(Neural Connesslessless Unesserpressor)和报告艺术压缩率和模型大小。