Abstract | ||
---|---|---|
•Open set detection using the maximum logit score of a softmax classifier matches the current state of the art.•Familiarity Hypothesis: The Max Logit method detects the absence of familiarity rather than the presence of novelty.•The reduced activity of positively-weighted object-relevant features accounts for most of the Max Logit score. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.patcog.2022.108931 | Pattern Recognition |
Keywords | DocType | Volume |
Anomaly detection,Open set learning,Computer vision,Object recognition,Novel category detection,Representation learning,Deep learning | Journal | 132 |
Issue | ISSN | Citations |
1 | 0031-3203 | 0 |
PageRank | References | Authors |
0.34 | 0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Thomas G. Dietterich | 1 | 9336 | 1722.57 |
Alexander Guyer | 2 | 0 | 0.34 |