Full-spectrum out-of-distribution (F-OOD) detection aims to accurately recognize in-distribution (ID) samples while encountering semantic and covariate shifts simultaneously. However, existing out-of-distribution (OOD) detectors tend to overfit the covariance information and ignore intrinsic semantic correlation, inadequate for adapting to complex domain transformations. To address this issue, we propose a Likelihood-Aware Semantic Alignment (LSA) framework to promote the image-text correspondence into semantically high-likelihood regions. LSA consists of an offline Gaussian sampling strategy which efficiently samples semantic-relevant visual embeddings from the class-conditional Gaussian distribution, and a bidirectional prompt customization mechanism that adjusts both ID-related and negative context for discriminative ID/OOD boundary. Extensive experiments demonstrate the remarkable OOD detection performance of our proposed LSA especially on the intractable Near-OOD setting, surpassing existing methods by a margin of $15.26\%$ and $18.88\%$ on two F-OOD benchmarks, respectively.

翻译：全谱分布外检测旨在同时应对语义变化和协变量偏移，准确识别分布内样本。然而，现有分布外检测器往往过度拟合协方差信息而忽视内在语义关联，难以适应复杂域变换。针对该问题，我们提出似然感知语义对齐框架（LSA），通过将图像-文本对应关系推向语义高似然区域。LSA包含离线高斯采样策略（离线采样类条件高斯分布中的语义相关视觉嵌入）与双向提示定制机制（联合调整分布内相关与负向上下文以构建判别性分布内/分布外边界）。大量实验表明，所提LSA方法尤其在难解近分布外场景中展现出卓越的分布外检测性能，在两个全谱分布外基准测试上分别以$15.26\%$和$18.88\%$的幅度超越现有方法。