Fast ConvNets Using Group-wise Brain Damage
We revisit the idea of brain damage, i.e. the pruning of the coefficients of a neural network, and suggest how brain damage can be modified and used to speedup convolutional layers. The approach uses the fact that many efficient implementations reduce generalized convolutions to matrix multiplications. The suggested brain damage process prunes the convolutional kernel tensor in a group-wise fashion by adding group-sparsity regularization to the standard training process. After such group-wise pruning, convolutions can be reduced to multiplications of thinned dense matrices, which leads to speedup. In the comparison on AlexNet, the method achieves very competitive performance.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Multiple-View Spectral Clustering for Group-wise Functional Community Detection
Functional connectivity analysis yields powerful insights into our understanding of the human brain. Group-wise functional community detection aims to partition the brain into clusters, or communities, in which functiona…
ClusteringCommunity DetectionFunctional ConnectivityInterpret Vision Transformers as ConvNets with Dynamic Convolutions
There has been a debate about the superiority between vision Transformers and ConvNets, serving as the backbone of computer vision models. Although they are usually considered as two completely different architectures, i…
Deep Radiomics for Brain Tumor Detection and Classification from Multi-Sequence MRI
Glioma constitutes 80% of malignant primary brain tumors and is usually classified as HGG and LGG. The LGG tumors are less aggressive, with slower growth rate as compared to HGG, and are responsive to therapy. Tumor biop…
General ClassificationTransfer LearningResidual Gated Graph ConvNets
Graph-structured data such as social networks, functional brain networks, gene regulatory networks, communications networks have brought the interest in generalizing deep learning techniques to graph domains. In this pap…
ClusteringGeneral ClassificationGraph ClassificationGraph Clustering+3Deep Symmetry Networks
The chief difficulty in object recognition is that objects' classes are obscured by a large number of extraneous sources of variability, such as pose and part deformation. These sources of variation can be represented by…
Object RecognitionTranslation