paper-with-me

홈 › Papers

Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters

2020-09-25 · Xudong Wang, Stella X. Yu

Convolution is the main building block of convolutional neural networks (CNN). We observe that an optimized CNN often has highly correlated filters as the number of channels increases with depth, reducing the expressive power of feature representations. We propose Tied Block Convolution (TBC) that shares the same thinner filters over equal blocks of channels and produces multiple responses with a single filter. The concept of TBC can also be extended to group convolution and fully connected layers, and can be applied to various backbone networks and attention modules. Our extensive experimentation on classification, detection, instance segmentation, and attention demonstrates TBC's significant across-the-board gain over standard convolution and group convolution. The proposed TiedSE attention module can even use 64 times fewer parameters than the SE module to achieve comparable performance. In particular, standard CNNs often fail to accurately aggregate information in the presence of occlusion and result in multiple redundant partial object proposals. By sharing filters across channels, TBC reduces correlation and can effectively handle highly overlapping instances. TBC increases the average precision for object detection on MS-COCO by 6% when the occlusion ratio is 80%. Our code will be released.

📄 PDF Abstract BibTeX arXiv:2009.12021

Code (1)

frank-xwang/TBC-TiedBlockConvolution pytorch

Tasks

Instance Segmentationobject-detectionObject DetectionSemantic Segmentation

Methods 이 논문이 사용한 방법론

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…

Similar Papers 제목 키워드 기반

Tiled convolutional neural networks

2010-12-01 · NeurIPS 2010 12 · Jiquan Ngiam, Zhenghao Chen, Daniel Chia, Pang W. Koh 외

Convolutional neural networks (CNNs) have been successfully applied to many tasks such as digit and object recognition. Using convolutional (tied) weights significantly reduces the number of parameters that have to be lea…

Object Recognition

Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition

2020-07-22 · Sudhakar Kumawat, Manisha Verma, Yuta Nakashima, Shanmuganathan Raman

Conventional 3D convolutional neural networks (CNNs) are computationally expensive, memory intensive, prone to overfitting, and most importantly, there is a need to improve their feature learning capabilities. To address…

Action RecognitionTemporal Action Localization

Exploring Temporal Differences in 3D Convolutional Neural Networks

2019-09-07 · Gagan Kanojia, Sudhakar Kumawat, Shanmuganathan Raman

Traditional 3D convolutions are computationally expensive, memory intensive, and due to large number of parameters, they often tend to overfit. On the other hand, 2D CNNs are less computationally expensive and less memor…

image-classificationImage ClassificationObject Recognition

Harmonic Networks: Integrating Spectral Information into CNNs

2018-12-07 · Matej Ulicny, Vladimir A. Krylov, Rozenn Dahyot

Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. In contrast, in this paper we propose harmonic blocks that produce features by learning optimal combinat…

General Classification

Convolution-Free Medical Image Segmentation using Transformers

2021-02-26 · Davood Karimi, Serge Vasylechko, Ali Gholipour

Like other applications in computer vision, medical image segmentation has been most successfully addressed using deep learning models that rely on the convolution operation as their main building block. Convolutions enj…

Image SegmentationInductive BiasMedical Image SegmentationSegmentation+2