Search Results for author:
Found 2 papers, 1 papers with code
Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detection
Logit smoothing computes the cosine similarity between the feature vector of the test sample and the prototype of the predicted ID class at the penultimate layer and uses the similarity as an adaptive temperature factor on the logit to alleviate the network's overconfidence prediction for OOD data.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
SATS: Self-Attention Transfer for Continual Semantic Segmentation
Considering that pixels belonging to the same class in each image often share similar visual properties, a class-specific region pooling is applied to provide more efficient relationship information for knowledge transfer.
Ranked #1 on
Overlapped 25-25
on ADE20K
