A new framework adds adaptive background patch suppression via entropy weighting and confusable foreground patch rectification to existing FG-BG methods, significantly improving few-shot OOD detection.
Opencil: Benchmarking out-of-distribution detec- tion in class incremental learning.Pattern Recognition, 171:112163,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Enhancing Few-Shot Out-of-Distribution Detection via the Refinement of Foreground and Background
A new framework adds adaptive background patch suppression via entropy weighting and confusable foreground patch rectification to existing FG-BG methods, significantly improving few-shot OOD detection.