paper-with-me

Papers

Enhancing Batch Normalized Convolutional Networks using Displaced Rectifier Linear Units: A Systematic Comparative Study

2018-01-01 · ICLR 2018 1 · David Macêdo, Cleber Zanchettin, Adriano L. I. Oliveira, Teresa Ludermir

In this paper, we turn our attention to the interworking between the activation functions and the batch normalization, which is a virtually mandatory technique to train deep networks currently. We propose the activation function Displaced Rectifier Linear Unit (DReLU) by conjecturing that extending the identity function of ReLU to the third quadrant enhances compatibility with batch normalization. Moreover, we used statistical tests to compare the impact of using distinct activation functions (ReLU, LReLU, PReLU, ELU, and DReLU) on the learning speed and test accuracy performance of standardized VGG and Residual Networks state-of-the-art models. These convolutional neural networks were trained on CIFAR-100 and CIFAR-10, the most commonly used deep learning computer vision datasets. The results showed DReLU speeded up learning in all models and datasets. Besides, statistical significant performance assessments (p<0.05) showed DReLU enhanced the test accuracy presented by ReLU in all scenarios. Furthermore, DReLU showed better test accuracy than any other tested activation function in all experiments with one exception, in which case it presented the second best performance. Therefore, this work demonstrates that it is possible to increase performance replacing ReLU by an enhanced activation function.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

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…
Batch Normalization 설명 없음
Average Pooling 설명 없음
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
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Similar Papers 제목 키워드 기반

Batch-normalized Maxout Network in Network

2015-11-09 · Jia-Ren Chang, Yong-Sheng Chen

This paper reports a novel deep architecture referred to as Maxout network In Network (MIN), which can enhance model discriminability and facilitate the process of information abstraction within the receptive field. The …

Image Classification

Kernel Normalized Convolutional Networks

2022-05-20 · Reza Nasirigerdeh, Reihaneh Torkzadehmahani, Daniel Rueckert, Georgios Kaissis

Existing convolutional neural network architectures frequently rely upon batch normalization (BatchNorm) to effectively train the model. BatchNorm, however, performs poorly with small batch sizes, and is inapplicable to …

Federated Learningimage-classificationImage ClassificationSemantic Segmentation

Normalized Convolutional Neural Network

2020-05-11 · Dongsuk Kim, Geonhee Lee, Myungjae Lee, Shin Uk Kang 외

In this paper, we propose Normalized Convolutional Neural Network(NCNN). NCNN is more fitted to a convolutional operator than other nomralizaiton methods. The normalized process is similar to a normalization methods, but…

Convolutional Rectifier Networks as Generalized Tensor Decompositions

2016-03-01 · Nadav Cohen, Amnon Shashua

Convolutional rectifier networks, i.e. convolutional neural networks with rectified linear activation and max or average pooling, are the cornerstone of modern deep learning. However, despite their wide use and success, …

On the Space-Time Statistics of Motion Pictures

2021-01-29 · Dae Yeol Lee, Hyunsuk Ko, Jongho Kim, Alan C. Bovik

It is well-known that natural images possess statistical regularities that can be captured by bandpass decomposition and divisive normalization processes that approximate early neural processing in the human visual syste…

Optical Flow Estimation