Fully Hyperbolic Convolutional Neural Networks
Convolutional Neural Networks (CNN) have recently seen tremendous success in various computer vision tasks. However, their application to problems with high dimensional input and output, such as high-resolution image and video segmentation or 3D medical imaging, has been limited by various factors. Primarily, in the training stage, it is necessary to store network activations for back propagation. In these settings, the memory requirements associated with storing activations can exceed what is feasible with current hardware, especially for problems in 3D. Motivated by the propagation of signals over physical networks, that are governed by the hyperbolic Telegraph equation, in this work we introduce a fully conservative hyperbolic network for problems with high dimensional input and output. We introduce a coarsening operation that allows completely reversible CNNs by using a learnable Discrete Wavelet Transform and its inverse to both coarsen and interpolate the network state and change the number of channels. We show that fully reversible networks are able to achieve results comparable to the state of the art in 4D time-lapse hyper spectral image segmentation and full 3D video segmentation, with a much lower memory footprint that is a constant independent of the network depth. We also extend the use of such networks to Variational Auto Encoders with high resolution input and output.
Code (0)
등록된 구현이 없습니다.
Tasks
Depth EstimationGeneral ClassificationImage ClassificationImage SegmentationSegmentationSemantic SegmentationVideo SegmentationVideo Semantic SegmentationSimilar Papers 제목 키워드 기반
Fully Hyperbolic Convolutional Neural Networks for Computer Vision
Real-world visual data exhibit intrinsic hierarchical structures that can be represented effectively in hyperbolic spaces. Hyperbolic neural networks (HNNs) are a promising approach for learning feature representations i…
Image ClassificationImage GenerationDeepHGCN: Toward Deeper Hyperbolic Graph Convolutional Networks
Hyperbolic graph convolutional networks (HGCNs) have demonstrated significant potential in extracting information from hierarchical graphs. However, existing HGCNs are limited to shallow architectures due to the computat…
Computational EfficiencyLink PredictionNode ClassificationFFHR: Fully and Flexible Hyperbolic Representation for Knowledge Graph Completion
Learning hyperbolic embeddings for knowledge graph (KG) has gained increasing attention due to its superiority in capturing hierarchies. However, some important operations in hyperbolic space still lack good definitions,…
Knowledge Graph CompletionRepresentation LearningHyperbolic Neural Networks++
Hyperbolic spaces, which have the capacity to embed tree structures without distortion owing to their exponential volume growth, have recently been applied to machine learning to better capture the hierarchical nature of…
BIG-bench Machine LearningregressionNested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design
Hyperbolic neural networks have been popular in the recent past due to their ability to represent hierarchical data sets effectively and efficiently. The challenge in developing these networks lies in the nonlinearity of…
Dimensionality Reduction