RAS is a plug-and-play OOD detection technique that applies ranked activation shifts to a fixed reference profile for stable discrimination without hyperparameters.
IEEE Signal Processing Magazine29(6), 141–142 (2012)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
DAR replaces GAP with an attention-based aggregation module retrained jointly with the classifier head to disentangle core from spurious features and outperforms DFR on multiple datasets.
citing papers explorer
-
Ranked Activation Shift for Post-Hoc Out-of-Distribution Detection
RAS is a plug-and-play OOD detection technique that applies ranked activation shifts to a fixed reference profile for stable discrimination without hyperparameters.
-
Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations
DAR replaces GAP with an attention-based aggregation module retrained jointly with the classifier head to disentangle core from spurious features and outperforms DFR on multiple datasets.
- Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition