Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters
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.
Code (1)
Tasks
Instance Segmentationobject-detectionObject DetectionSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Tiled convolutional neural networks
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 RecognitionDepthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition
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 LocalizationExploring Temporal Differences in 3D Convolutional Neural Networks
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 RecognitionHarmonic Networks: Integrating Spectral Information into CNNs
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 ClassificationConvolution-Free Medical Image Segmentation using Transformers
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