Feature-alteration Robustness for Out-of-distribution Detection.
It is found that a well-pretrained in-distribution model can memorize and recognize ID patterns, even when the features undergo alterations, even when the features undergo alterations.
We have 2 of 10 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
It is found that a well-pretrained in-distribution model can memorize and recognize ID patterns, even when the features undergo alterations, even when the features undergo alterations.
This work proposes REVERIE+ (ReflEctiVERatIonalE), an extension of REVERIE substantially expanded in domain diversity, task complexity, and annotation richness, tailored to advanced LVLMs, which broadens domain coverage and increases task difficulty, while improving annotation reliability.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.