A modified Classification-by-Components network with negative reasoning and provable robustness bounds beats existing deep prototype models on fine-grained image benchmarks.
E.; Chortis, V.; Sitch, A
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Robust Prototype-Based Network with Interpretable RBF Classifier Foundations
A modified Classification-by-Components network with negative reasoning and provable robustness bounds beats existing deep prototype models on fine-grained image benchmarks.