DiCENet: Dimension-wise Convolutions for Efficient Networks

06/08/2019
by   Sachin Mehta, et al.
4

In this paper, we propose a new CNN model DiCENet, that is built using: (1) dimension-wise convolutions and (2) efficient channel fusion. The introduced blocks maximize the use of information in the input tensor by learning representations across all dimensions while simultaneously reducing the complexity of the network and achieving high accuracy. Our model shows significant improvements over state-of-the-art models across various visual recognition tasks, including image classification, object detection, and semantic segmentation. Our model delivers either the same or better performance than existing models with fewer FLOPs, including task-specific models. Notably, DiCENet delivers competitive performance to neural architecture search-based methods at fewer FLOPs (70-100 MFLOPs). On the MS-COCO object detection, DiCENet is 4.5 PASCAL VOC 2012 semantic segmentation dataset, DiCENet is 4.3 and has 3.2 times fewer FLOPs than a recent efficient semantic segmentation network, ESPNet. Our source code is available at <https://github.com/sacmehta/EdgeNets>

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/28/2018

ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network

We introduce a light-weight, power efficient, and general purpose convol...
research
07/23/2020

Funnel Activation for Visual Recognition

We present a conceptually simple but effective funnel activation for ima...
research
03/18/2019

IvaNet: Learning to jointly detect and segment objets with the help of Local Top-Down Modules

Driven by Convolutional Neural Networks, object detection and semantic s...
research
10/30/2022

SL3D: Self-supervised-Self-labeled 3D Recognition

There are a lot of promising results in 3D recognition, including classi...
research
03/31/2020

MUXConv: Information Multiplexing in Convolutional Neural Networks

Convolutional neural networks have witnessed remarkable improvements in ...
research
05/14/2019

Efficient Ladder-style DenseNets for Semantic Segmentation of Large Images

Recent progress of deep image classification models has provided great p...
research
06/05/2019

Butterfly Transform: An Efficient FFT Based Neural Architecture Design

In this paper, we introduce the Butterfly Transform (BFT), a light weigh...

Please sign up or login with your details

Forgot password? Click here to reset