Miscellaneous Components

Auxiliary Classifier

Auxiliary Classifiers are type of architectural component that seek to improve the convergence of very deep networks. They are classifier heads we attach to layers before the end of the network. The motivation is to push useful gradients to the lower layers to make them immediately useful and improve the convergence during training by combatting the vanishing gradient problem. They are notably used in the Inception family of convolutional neural networks.


Paper Code Results Date Stars


Task Papers Share
Image Classification 53 8.63%
General Classification 47 7.65%
Semantic Segmentation 43 7.00%
Classification 41 6.68%
Object Detection 24 3.91%
Quantization 18 2.93%
Image Segmentation 13 2.12%
Image Generation 12 1.95%
Object Recognition 11 1.79%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign