Efficient Accelerator for Dilated and Transposed Convolution with Decomposition

2 May 2022 · Kuo-Wei Chang, Tian-Sheuan Chang ·

Hardware acceleration for dilated and transposed convolution enables real time execution of related tasks like segmentation, but current designs are specific for these convolutional types or suffer from complex control for reconfigurable designs. This paper presents a design that decomposes input or weight for dilated and transposed convolutions respectively to skip redundant computations and thus executes efficiently on existing dense CNN hardware as well. The proposed architecture can cut down 87.8\% of the cycle counts to achieve 8.2X speedup over a naive execution for the ENet case.

PDF Abstract

Code

Add Remove Mark official

No code implementations yet. Submit your code now

Tasks

Add Remove

Datasets

Add Datasets introduced or used in this paper

Results from the Paper

Edit

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods

Add Remove

1x1 Convolution • Batch Normalization • Convolution • Dilated Convolution • ENet • ENet Bottleneck • ENet Dilated Bottleneck • ENet Initial Block • Max Pooling • PReLU • SpatialDropout • Transposed convolution

Edit Social Preview

Efficient Accelerator for Dilated and Transposed Convolution with Decomposition

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove