Recent research has shown that pre-trained vision-language models are effective at identifying out-of-distribution (OOD) samples by using negative labels as guidance. However, employing consistent negative labels across different OOD datasets often results in semantic misalignments, as these text labels may not accurately reflect the actual space of OOD images. To overcome this issue, we introduce \textit{adaptive negative proxies}, which are dynamically generated during testing by exploring actual OOD images, to align more closely with the underlying OOD label space and enhance the efficacy of negative proxy guidance. Specifically, our approach utilizes a feature memory bank to selectively cache discriminative features from test images, representing the targeted OOD distribution. This facilitates the creation of proxies that can better align with specific OOD datasets.

Pseudo-labeling has emerged as a popular and effective approach for utilizing unlabeled data.

Themostpopular fashion of SSFSL is to predict unlabeled data with pseudo-labels by carefully devising tailored strategies, and then augment the extremely small support set of labeled data in few-shot classification,e.g., [9,15,36].

Discrimination is commonly an issue in applications where decisions need to be made sequentially. The most prominent such application is online advertising where platforms need to sequentially select which ad to display in response to particular query searches.

Pseudo-labeling has emerged as a popular and effective approach for utilizing unlabeled data.