Integrating Multiple Receptive Fields through Grouped Active Convolution

2018-11-11 · Yunho Jeon, Junmo Kim

Convolutional networks have achieved great success in various vision tasks. This is mainly due to a considerable amount of research on network structure. In this study, instead of focusing on architectures, we focused on the convolution unit itself. The existing convolution unit has a fixed shape and is limited to observing restricted receptive fields. In earlier work, we proposed the active convolution unit (ACU), which can freely define its shape and learn by itself. In this paper, we provide a detailed analysis of the previously proposed unit and show that it is an efficient representation of a sparse weight convolution. Furthermore, we extend an ACU to a grouped ACU, which can observe multiple receptive fields in one layer. We found that the performance of a naive grouped convolution is degraded by increasing the number of groups; however, the proposed unit retains the accuracy even though the number of parameters decreases. Based on this result, we suggest a depthwise ACU, and various experiments have shown that our unit is efficient and can replace the existing convolutions.

📄 PDF Abstract BibTeX arXiv:1811.04387

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Active Convolution An Active Convolution is a type of convolution which does not have a fixed shape of the receptive field, and can be used to…

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Grouped Convolution A Grouped Convolution uses a group of convolutions - multiple kernels per layer - resulting in multiple channel outputs per layer. This leads to wider networks helping a…

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…

Unsupervised learning models of primary cortical receptive fields and receptive field plasticity

2011-12-01 · NeurIPS 2011 12 · Maneesh Bhand, Ritvik Mudur, Bipin Suresh, Andrew Saxe 외

The efficient coding hypothesis holds that neural receptive fields are adapted to the statistics of the environment, but is agnostic to the timescale of this adaptation, which occurs on both evolutionary and developmenta…

PARF-Net: integrating pixel-wise adaptive receptive fields into hybrid Transformer-CNN network for medical image segmentation

2025-01-06 · Xu Ma, Mengsheng Chen, Junhui Zhang, Lijuan Song 외

Convolutional neural networks (CNNs) excel in local feature extraction while Transformers are superior in processing global semantic information. By leveraging the strengths of both, hybrid Transformer-CNN networks have …

Image Segmentation Medical Image Segmentation Semantic Segmentation

Normative theory of visual receptive fields

2017-01-23 · Tony Lindeberg

This article gives an overview of a normative computational theory of visual receptive fields, by which idealized functional models of early spatial, spatio-chromatic and spatio-temporal receptive fields can be derived i…

Crowd counting via scale-adaptive convolutional neural network

2017-11-13 · Lu Zhang, Miaojing Shi, Qiaobo Chen

The task of crowd counting is to automatically estimate the pedestrian number in crowd images. To cope with the scale and perspective changes that commonly exist in crowd images, state-of-the-art approaches employ multi-…

Crowd Counting

Multi-Resolution Fusion for Fully Automatic Cephalometric Landmark Detection

2023-10-04 · Dongqian Guo, Wencheng Han

Cephalometric landmark detection on lateral skull X-ray images plays a crucial role in the diagnosis of certain dental diseases. Accurate and effective identification of these landmarks presents a significant challenge. …

Data Augmentation