Deep Residual Learning for Image Recognition
Explore this paper's citation graph
Summary
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
- Type
- article
- Published
- 2015-12-10
- Cited by
- 237,744
- References
- 54
- Access
- Open access
- OpenAlex
- https://openalex.org/W2194775991
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:206594692
Keywords
Residual, Computer science, Coco, Artificial intelligence, Object detection
References
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Training Very Deep Networks
- A multigrid tutorial
- Understanding the difficulty of training deep feedforward neural networks
- Pattern Recognition and Neural Networks
- Rectified Linear Units Improve Restricted Boltzmann Machines
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Pushing Stochastic Gradient towards Second-Order Methods -- Backpropagation Learning with Transformations in Nonlinearities
- Fully convolutional networks for semantic segmentation
- Improving neural networks by preventing co-adaptation of feature detectors
- Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model
- Convolutional neural networks at constrained time cost
- The devil is in the details: an evaluation of recent feature encoding methods
- Aggregating Local Image Descriptors into Compact Codes
- Locally adapted hierarchical basis preconditioning
- The Pascal Visual Object Classes (VOC) Challenge
- Long Short-Term Memory
- Vlfeat: an open and portable library of computer vision algorithms
- Going deeper with convolutions
Cited by
- Automatic Image-Based Plant Disease Severity Estimation Using Deep Learning
- Person Reidentification via Discrepancy Matrix and Matrix Metric
- Parallel Distributed Processing Theory in the Age of Deep Networks.
- Skin Lesion Analysis towards Melanoma Detection Using Deep Learning Network
- A deep 3D residual CNN for false-positive reduction in pulmonary nodule detection.
- Deep learning and medical imaging.
- Efficient and self-adaptive in-situ learning in multilayer memristor neural networks
- Fine-Tuning CNN Image Retrieval with No Human Annotation
- Monocular Depth Estimation Using Multi-Scale Continuous CRFs as Sequential Deep Networks
- Interpreting Deep Visual Representations via Network Dissection
- Unsupervised Knowledge Transfer Using Similarity Embeddings
- Automatic hyoid bone detection in fluoroscopic images using deep learning
- Deep Crisp Boundaries: From Boundaries to Higher-Level Tasks
- Video-Based Person Re-Identification by an End-To-End Learning Architecture with Hybrid Deep Appearance-Temporal Feature
- PhotoAgeClock: deep learning algorithms for development of non-invasive visual biomarkers of aging
- Segmentation of Both Diseased and Healthy Skin From Clinical Photographs in a Primary Care Setting
- Automatic brain labeling via multi‐atlas guided fully convolutional networks☆
- Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding
- Feature Boosting Network For 3D Pose Estimation
- Features Combined From Hundreds of Midlayers: Hierarchical Networks With Subnetwork Nodes
Related papers
- Skin Disease Diagnostic techniques using deep learning
- Performance evaluation of 2D and 3D deep learning approaches for automatic segmentation of multiple organs on CT images
- Efficient Disease Risk Prediction based on Deep Learning Approach
- A Survey on Deep Learning Models Embed Bio-Inspired Algorithms in Cardiac Disease Classification
- A Comprehensive Analysis of Machine Learning Techniques in Biomedical Image Processing Using Convolutional Neural Network
- Machine Learning and Deep Learning applications-a vision using the SPSS Method
- Deep Learning for Object Detection and Grasping: A Survey
- Optimized Deep Convolutional Neural Networks for Identification of Macular Diseases from Optical Coherence Tomography Images
- Novel CNN architecture with residual learning and deep supervision for large-scale scene image categorization