IC-Network: Efficient Structure for Convolutional Neural Networks

2019-11-19 · Junyi An, Fengshan Liu, Jian Zhao, Furao Shen

Neural networks have been widely used, and most networks achieve excellent performance by stacking certain types of basic units. Compared to increasing the depth and width of the network, designing more effective basic units has become an important research topic. Inspired by the elastic collision model in physics, we present a universal structure that could be integrated into the existing network structures to speed up the training process and increase their generalization abilities. We term this structure the "Inter-layer Collision" (IC) structure. We built two kinds of basic computational units (IC layer and IC block) that compose the convolutional neural networks (CNNs) by combining the IC structure with the convolution operation. Compared to traditional convolutions, both of the proposed computational units have a stronger non-linear representation ability and can filter features useful for a given task. Using these computational units to build networks, we bring significant improvements in performance for existing state-of-the-art CNNs. On the imagenet experiment, we integrate the IC block into ResNet-50 and reduce the top-1 error from 22.85% to 21.49%, which also exceeds the top-1 error of ResNet-100 (21.75%).

📄 PDF Abstract BibTeX arXiv:1911.08252

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification Image Classification

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Mesh-based graph convolutional neural networks for modeling materials with microstructure

2021-06-04 · Ari Frankel, Cosmin Safta, Coleman Alleman, Reese Jones

Predicting the evolution of a representative sample of a material with microstructure is a fundamental problem in homogenization. In this work we propose a graph convolutional neural network that utilizes the discretized…

Training Structured Efficient Convolutional Layers

2018-10-20 · Gavin Gray, Elliot Crowley, Amos Storkey

Typical recent neural network designs are primarily convolutional layers, but the tricks enabling structured efficient linear layers (SELLs) have not yet been adapted to the convolutional setting. We present a method to …

Computational Efficiency

Symmetry Structured Convolutional Neural Networks

2022-03-03 · Kehelwala Dewage Gayan Maduranga, Vasily Zadorozhnyy, Qiang Ye

We consider Convolutional Neural Networks (CNNs) with 2D structured features that are symmetric in the spatial dimensions. Such networks arise in modeling pairwise relationships for a sequential recommendation problem, a…

Sequential Recommendation

Coarse and fine-grained automatic cropping deep convolutional neural network

2020-10-13 · Jingfei Chang

The existing convolutional neural network pruning algorithms can be divided into two categories: coarse-grained clipping and fine-grained clipping. This paper proposes a coarse and fine-grained automatic pruning algorith…

Network Pruning

Structure-Based Drug-Drug Interaction Detection via Expressive Graph Convolutional Networks and Deep Sets

2022-01-20 · AAAI 2022 1 · Mengying Sun, Fei Wang, Olivier Elemento, Jiayu Zhou

In this work, we proposed a DDI detection method based on molecular structures using graph convolutional networks and deep sets. We proposed a more discriminative convolutional layer compared to conventional GCN and achi…