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.

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
General Classification 47 10.90%
Image Classification 45 10.44%
Semantic Segmentation 33 7.66%
Object Detection 20 4.64%
Quantization 16 3.71%
Image Generation 10 2.32%
Autonomous Driving 9 2.09%
Object Recognition 9 2.09%
Domain Adaptation 7 1.62%

Components


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

Categories