Scale-Invariant Convolutional Neural Networks
Explore this paper's citation graph
Summary
A scale-invariant convolutional neural network (SiCNN), a modeldesigned to incorporate multi-scale feature exaction and classification into the network structure, and results show that SiCNN detects features at various scales, and the classi-cation result exhibits strong robust-ness against object scale variations.
- Type
- preprint
- Published
- 2014-11-23
- Cited by
- 151
- References
- 20
- Access
- Open access
- OpenAlex
- https://openalex.org/W1800922288
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:18081714
Keywords
Convolutional neural network, Computer science, Robustness (evolution), Artificial intelligence, Scale (ratio)
References
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Improving neural networks by preventing co-adaptation of feature detectors
- Going deeper with convolutions
- ImageNet Large Scale Visual Recognition Challenge
- Practical Bayesian Optimization of Machine Learning Algorithms
- Multi-column deep neural networks for image classification
- Cubic convolution interpolation for digital image processing
- ImageNet classification with deep convolutional neural networks
- Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
- Visualizing and Understanding Convolutional Neural Networks
- Maxout Networks
- Network In Network
- Et al
- Learning Multiple Layers of Features from Tiny Images
- Multi-scale Orderless Pooling of Deep Convolutional Activation Features
- Visualizing and Understanding Convolutional Networks
- Convolutional networks for images, speech, and time series
- Visualizing Higher-Layer Features of a Deep Network
- Learning Multiple Layers of Features from Tiny Images
- Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
Cited by
- Scale-Aware Fast R-CNN for Pedestrian Detection
- Learning to Point and Count
- Learning scale-variant and scale-invariant features for deep image classification
- Improved RGB-D-T based face recognition
- PARTICLE SWARM OPTIMIZATION (PSO) FOR TRAINING OPTIMIZATION ON CONVOLUTIONAL NEURAL NETWORK (CNN)
- Using Multi-Stage Features in Fast R-CNN for Pedestrian Detection
- A Faster RCNN-Based Pedestrian Detection System
- Deep learning for situational understanding
- Resting State fMRI Functional Connectivity-Based Classification Using a Convolutional Neural Network Architecture
- Pedestrian Detection via Bi-directional Multi-scale Analysis
- Saliency Preservation in Low-Resolution Grayscale Images
- A scale-invariant framework for image classification with deep learning
- Non-Parametric Transformation Networks
- Retinal Lesion Detection With Deep Learning Using Image Patches
- Particle identification in camera image sensors using computer vision
- A neural network structure with wide range scale robustness
- Scale equivariance in CNNs with vector fields
- Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance
- Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures
- Steganalyzing Images of Arbitrary Size with CNNs
Related papers
- An Adaptable Real-Time Object Detection for Traffic Surveillance using R-CNN over CNN with Improved Accuracy
- Is Multiple-Column Online Text Better? It Depends!
- Ponders on Column Construction with Characteristics of Local University's Journals
- Column oriented Database Systems
- On the Format Planning of Columns in the Academic Journals and the Construction of the System of Editing Classification
- Distributed Computing Column 86
- Research on the Column Effect and Construction Measures of Social Scientific Journals of Colleges and Universities
- Researching robustness of information system for measuring of microcontrollers average power consumption
- When to Build an FAQ: A Case Study
- Convolutional Neural Network (CNN) Applied to the Risk Analysis of Accidents in Vessels Navigating the Amazon Rivers