ParaNet - Using Dense Blocks for Early Inference

24 Aug 2018 · Joseph Chuang, Eric Tsai, Kevin Huang, Jay Fetter ·

DenseNets have been shown to be a competitive model among recent convolutional network architectures. These networks utilize Dense Blocks, which are groups of densely connected layers where the output of a hidden layer is fed in as the input of every other layer following it. In this paper, we aim to improve certain aspects of DenseNet, especially when it comes to practicality. We introduce ParaNet, a new architecture that constructs three pipelines which allow for early inference. We additionally introduce a cascading mechanism such that different pipelines are able to share parameters, as well as logit matching between the outputs of the pipelines. We separately evaluate each of the newly introduced mechanisms of ParaNet, then evaluate our proposed architecture on CIFAR-100.

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 • Average Pooling • Batch Normalization • Concatenated Skip Connection • Convolution • Dense Block • Dense Connections • DenseNet • Dropout • Global Average Pooling • Kaiming Initialization • Max Pooling • ReLU • Softmax

Edit Social Preview

ParaNet - Using Dense Blocks for Early Inference

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