DetNet

Introduced by Li et al. in DetNet: A Backbone network for Object Detection

DetNet is a backbone convolutional neural network for object detection. Different from traditional pre-trained models for ImageNet classification, DetNet maintains the spatial resolution of the features even though extra stages are included. DetNet attempts to stay efficient by employing a low complexity dilated bottleneck structure.

Source: DetNet: A Backbone network for Object Detection

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Classification	2	13.33%
General Classification	2	13.33%
Image Classification	2	13.33%
Instance Segmentation	2	13.33%
Object	2	13.33%
Object Detection	2	13.33%
Semantic Segmentation	2	13.33%
Deep Learning	1	6.67%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
1x1 Convolution	Convolutions
Dilated Bottleneck Block	Skip Connection Blocks
Dilated Bottleneck with Projection Block	Skip Connection Blocks
Global Average Pooling	Pooling Operations
Residual Connection	Skip Connections

Categories

Add Remove

Convolutional Neural Networks