AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

RBF-Softmax: Learning Deep Representative Prototypes with Radial Basis Function Softmax

Xiao Zhang, Rui Zhao, Yu Qiao, Hongsheng Li

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 16 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace softmax inner-product logits with RBF-SoftmaxSoftmax · ImageNet ResNet-50top-1 accuracy: 76.8% -> 77.1%Improved
replace softmax with RBF-SoftmaxSoftmax · ImageNet EfficientNet-B1top-1 accuracy: 75.9% -> 76.6%Improved
replace softmax with RBF-SoftmaxSoftmax · ImageNet EfficientNet-B4top-1 accuracy: 78.8% -> 79.0%Improved
replace softmax with RBF-SoftmaxSoftmax · CIFAR-10 ResNet-20accuracy: 91.25% -> 92.77%Improved
replace softmax with RBF-SoftmaxSoftmax · MNIST 32-Daccuracy: 99.27% -> 99.73%Improved
replace softmax with RBF-SoftmaxSoftmax · CIFAR-100 VGGNet-19accuracy: 72.23% -> 73.98%Improved
replace softmax with RBF-SoftmaxSoftmax · CIFAR-100 prototypesCalinski-Harabaz index: 2.81 ± 0.21 -> 7.33 ± 0.25Improved
replace softmax with RBF-SoftmaxSoftmax · CIFAR-100 prototypessimilarity to WordNet matrix: 0.17 ± 0.05 -> 0.36 ± 0.11Improved
increase gamma from 1.0 to 2.0 (ablation)RBF-Softmax · MNIST 32-Daccuracy: 99.71% -> 99.42%Hurt
increase gamma from 1.0 to 4.0 (s=12) (ablation)RBF-Softmax · CIFAR-100 VGGNet-19accuracy: 72.62%±0.05% -> 71.77%±0.04%Hurt
increase s from 2.0 to 8.0 (ablation)RBF-Softmax · MNIST 32-Daccuracy: 99.71% -> 99.61%Hurt
increase s from 10 to 14 (gamma=2.2) (ablation)RBF-Softmax · CIFAR-100 VGGNet-19accuracy: 72.72%±0.03% -> 73.98%±0.02%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy