paper-with-me

Papers

Trainable Activations for Image Classification

2023-01-26 · Preprints 2023 1 · Evgenii Pishchik

Non-linear activation functions are one of the main parts of deep neural network architectures. The choice of the activation function can affect model speed, performance and convergence. Most popular activation functions don't have any trainable parameters and don't alter during the training. We propose different activation functions with and without trainable parameters. Said activation functions have a number of advantages and disadvantages. We'll be testing the performance of said activation functions and comparing the results with widely known activation function ReLU. We assume that the activation functions with trainable parameters can outperform functions without ones, because the trainable parameters allow the model to "select'' the type of each of the activation functions itself, however, this strongly depends on the architecture of the deep neural network and the activation function itself.

📄 PDF Abstract BibTeX

Code (1)

Pe4enIks/TrainableActivation 공식 구현 pytorch

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Residual Connection 설명 없음
Batch Normalization 설명 없음
Average Pooling 설명 없음
ShiLU The Shifted Rectified Linear Unit, or ShiLU, is a modification of ReLU activation function that has trainable…
ScaledSoftSign The ScaledSoftSign is a modification of SoftSign activation function that has trainable…
ReLUN The Rectified Linear Unit N, or ReLUN, is a modification of ReLU6 activation function that has trainable parameter…
ReLU6 ReLU6 is a modification of the rectified linear unit where we limit the activation to a maximum size of $6$. This is due to increased…

Similar Papers 제목 키워드 기반

Gaussian-Based Pooling for Convolutional Neural Networks

2019-12-01 · NeurIPS 2019 12 · Takumi Kobayashi

Convolutional neural networks (CNNs) contain local pooling to effectively downsize feature maps for increasing computation efficiency as well as robustness to input variations. The local pooling methods are generally for…

image-classificationImage Classification

Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning

2025-07-19 · Rafał Surdej, Michał Bortkiewicz, Alex Lewandowski, Mateusz Ostaszewski 외 arxiv

Trainable activation functions, whose parameters are optimized alongside network weights, offer increased expressivity compared to fixed activation functions. Specifically, trainable activation functions defined as ratio…

Reinforcement LearningContinuous ControlContinual Learning

Image Retrieval using Multi-scale CNN Features Pooling

2020-04-21 · Federico Vaccaro, Marco Bertini, Tiberio Uricchio, Alberto del Bimbo

In this paper, we address the problem of image retrieval by learning images representation based on the activations of a Convolutional Neural Network. We present an end-to-end trainable network architecture that exploits…

Image RetrievalRetrievalTriplet

Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks

2022-03-08 · Yunshan Zhong, Mingbao Lin, Xunchao Li, Ke Li 외

Light-weight super-resolution (SR) models have received considerable attention for their serviceability in mobile devices. Many efforts employ network quantization to compress SR models. However, these methods suffer fro…

QuantizationSuper-Resolution

Defending Against Universal Attacks Through Selective Feature Regeneration

2019-06-08 · CVPR 2020 6 · Tejas Borkar, Felix Heide, Lina Karam

Deep neural network (DNN) predictions have been shown to be vulnerable to carefully crafted adversarial perturbations. Specifically, image-agnostic (universal adversarial) perturbations added to any image can fool a targ…

Adversarial Defense