Feature Representation in Convolutional Neural Networks

2015-07-08 · Ben Athiwaratkun, Keegan Kang

Convolutional Neural Networks (CNNs) are powerful models that achieve impressive results for image classification. In addition, pre-trained CNNs are also useful for other computer vision tasks as generic feature extractors. This paper aims to gain insight into the feature aspect of CNN and demonstrate other uses of CNN features. Our results show that CNN feature maps can be used with Random Forests and SVM to yield classification results that outperforms the original CNN. A CNN that is less than optimal (e.g. not fully trained or overfitting) can also extract features for Random Forest/SVM that yield competitive classification accuracy. In contrast to the literature which uses the top-layer activations as feature representation of images for other tasks, using lower-layer features can yield better results for classification.

📄 PDF Abstract BibTeX arXiv:1507.02313

Code (0)

등록된 구현이 없습니다.

Tasks

Classification General Classification image-classification Image Classification

Methods 이 논문이 사용한 방법론

SVM A Support Vector Machine, or SVM, is a non-parametric supervised learning model. For non-linear classification and regression, they utilise the kernel trick to map inputs…

Co-occurrence of deep convolutional features for image search

2020-03-30 · J. I. Forcen, Miguel Pagola, Edurne Barrenechea, Humberto Bustince

Image search can be tackled using deep features from pre-trained Convolutional Neural Networks (CNN). The feature map from the last convolutional layer of a CNN encodes descriptive information from which a discriminative…

Descriptive Image Retrieval Retrieval

Locally-Supervised Deep Hybrid Model for Scene Recognition

2016-01-27 · Sheng Guo, Weilin Huang, Li-Min Wang, Yu Qiao

Convolutional neural networks (CNN) have recently achieved remarkable successes in various image classification and understanding tasks. The deep features obtained at the top fully-connected layer of the CNN (FC-features…

General Classification image-classification Image Classification model+1

Investigating Map-Based Path Loss Models: A Study of Feature Representations in Convolutional Neural Networks

2025-01-13 · Ryan G. Dempsey, Jonathan Ethier, Halim Yanikomeroglu

Path loss prediction is a beneficial tool for efficient use of the radio frequency spectrum. Building on prior research on high-resolution map-based path loss models, this paper studies convolutional neural network input…

Learning a Robust Representation via a Deep Network on Symmetric Positive Definite Manifolds

2017-11-17 · Zhi Gao, Yuwei Wu, Xingyuan Bu, Yunde Jia

Recent studies have shown that aggregating convolutional features of a pre-trained Convolutional Neural Network (CNN) can obtain impressive performance for a variety of visual tasks. The symmetric Positive Definite (SPD)…

REFINED (REpresentation of Features as Images with NEighborhood Dependencies): A novel feature representation for Convolutional Neural Networks

2019-12-11 · Omid Bazgir, Ruibo Zhang, Saugato Rahman Dhruba, Raziur Rahman 외

Deep learning with Convolutional Neural Networks has shown great promise in various areas of image-based classification and enhancement but is often unsuitable for predictive modeling involving non-image based features o…

Deep Learning feature selection