paper-with-me

Papers

Channel selection using Gumbel Softmax

2018-12-11 · ECCV 2020 8 · Charles Herrmann, Richard Strong Bowen, Ramin Zabih

Important applications such as mobile computing require reducing the computational costs of neural network inference. Ideally, applications would specify their preferred tradeoff between accuracy and speed, and the network would optimize this end-to-end, using classification error to remove parts of the network. Increasing speed can be done either during training - e.g., pruning filters - or during inference - e.g., conditionally executing a subset of the layers. We propose a single end-to-end framework that can improve inference efficiency in both settings. We use a combination of batch activation loss and classification loss, and Gumbel reparameterization to learn network structure. We train end-to-end, and the same technique supports pruning as well as conditional computation. We obtain promising experimental results for ImageNet classification with ResNet (45-52% less computation).

📄 PDF Abstract BibTeX arXiv:1812.04180

Code (1)

irwinherrmann/stochastic-gates 공식 구현 pytorch

Tasks

channel selectionClassificationGeneral Classification

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Gumbel Softmax 설명 없음
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

End-to-end learnable EEG channel selection for deep neural networks with Gumbel-softmax

2021-02-11 · Thomas Strypsteen, Alexander Bertrand

Many electroencephalography (EEG) applications rely on channel selection methods to remove the least informative channels, e.g., to reduce the amount of electrodes to be mounted, to decrease the computational load, or to…

channel selectionEEGElectroencephalogram (EEG)Motor Imagery

Conditional Gumbel-Softmax for constrained feature selection with application to node selection in wireless sensor networks

2024-06-03 · Thomas Strypsteen, Alexander Bertrand

In this paper, we introduce Conditional Gumbel-Softmax as a method to perform end-to-end learning of the optimal feature subset for a given task and deep neural network (DNN) model, while adhering to certain pairwise con…

EEGfeature selection

Gumbel-Softmax Selective Networks

2022-11-19 · Mahmoud Salem, Mohamed Osama Ahmed, Frederick Tung, Gabriel Oliveira

ML models often operate within the context of a larger system that can adapt its response when the ML model is uncertain, such as falling back on safe defaults or a human in the loop. This commonly encountered operationa…

Gradient Estimation with Stochastic Softmax Tricks

2020-06-15 · NeurIPS 2020 12 · Max B. Paulus, Dami Choi, Daniel Tarlow, Andreas Krause 외

The Gumbel-Max trick is the basis of many relaxed gradient estimators. These estimators are easy to implement and low variance, but the goal of scaling them comprehensively to large combinatorial distributions is still o…

Indirectly Parameterized Concrete Autoencoders

2024-03-01 · Alfred Nilsson, Klas Wijk, Sai Bharath Chandra Gutha, Erik Englesson 외

Feature selection is a crucial task in settings where data is high-dimensional or acquiring the full set of features is costly. Recent developments in neural network-based embedded feature selection show promising result…

Decoderfeature selection