Description
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.
Papers Using This Method
Federated Dynamic Neural Network for Deep MIMO Detection2021-11-24Green DetNet: Computation and Memory efficient DetNet using Smart Compression and Training2020-03-20Deep Learning-Aided Tabu Search Detection for Large MIMO Systems2019-09-04DetNet: Design Backbone for Object Detection2018-09-01DetNet: A Backbone network for Object Detection2018-04-17