Irregular Convolutional Neural Networks
Convolutional kernels are basic and vital components of deep Convolutional Neural Networks (CNN). In this paper, we equip convolutional kernels with shape attributes to generate the deep Irregular Convolutional Neural Networks (ICNN). Compared to traditional CNN applying regular convolutional kernels like ${3\times3}$, our approach trains irregular kernel shapes to better fit the geometric variations of input features. In other words, shapes are learnable parameters in addition to weights. The kernel shapes and weights are learned simultaneously during end-to-end training with the standard back-propagation algorithm. Experiments for semantic segmentation are implemented to validate the effectiveness of our proposed ICNN.
Code (0)
등록된 구현이 없습니다.
Tasks
Semantic SegmentationSimilar Papers 제목 키워드 기반
Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series
Irregularly sampled multivariate time series are ubiquitous in several application domains, leading to sparse, not fully-observed and non-aligned observations across different variables. Standard sequential neural networ…
Irregular Time SeriesTime SeriesConvolutional neural networks on irregular domains based on approximate vertex-domain translations
We propose a generalization of convolutional neural networks (CNNs) to irregular domains, through the use of a translation operator on a graph structure. In regular settings such as images, convolutional layers are desig…
TranslationGeneralizing the Convolution Operator to extend CNNs to Irregular Domains
Convolutional Neural Networks (CNNs) have become the state-of-the-art in supervised learning vision tasks. Their convolutional filters are of paramount importance for they allow to learn patterns while disregarding their…
EXIT-chart aided near-capacity Irregular Bit-Interleaved Coded Modulation design
A near-capacity irregular bit-interleaved coded modulation based iterative decoding (Ir-BICM-ID) aided scheme is proposed. The irregular design of the scheme pervades the three basic components of BICM-ID, namely the enc…
UnityAnalysis of Irregular Spatial Data with Machine Learning: Classification of Building Patterns with a Graph Convolutional Neural Network
Machine learning methods such as convolutional neural networks (CNNs) are becoming an integral part of scientific research in many disciplines, spatial vector data often fail to be analyzed using these powerful learning …
General Classification