PC-Softmax

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision6 results

Image ClassificationonImbalanced CUB-200-2011
Accuracy· 2019-11-25
89.73
best: 99.67 (Multi-task)
SOTA
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator arXiv:1911.10688
Image ClassificationonImbalanced CUB-200-2011
Average Per-Class Accuracy· 2019-11-25
87.69
SOTA
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator arXiv:1911.10688
Fine-Grained Image ClassificationonImbalanced CUB-200-2011
Accuracy· 2019-11-25
89.73
SOTA
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator arXiv:1911.10688
Fine-Grained Image ClassificationonImbalanced CUB-200-2011
Average Per-Class Accuracy· 2019-11-25
87.69
SOTA
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator arXiv:1911.10688
Image ClassificationonImbalanced CUB-200-2011
Accuracy· 2019-11-25
89.73
best: 99.67 (Multi-task)
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator arXiv:1911.10688
Image ClassificationonImbalanced CUB-200-2011
Average Per-Class Accuracy· 2019-11-25
87.69
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator arXiv:1911.10688