Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
Explore this paper's citation graph
Summary
This paper starts from a group of relatively shallow networks, which perform as well or even better than the current state-of-the-art models on the ImageNet classification dataset, and initialize fully convolutional networks (FCNs) using pre-trained models, and tune them for semantic image segmentation.
- Type
- article
- Published
- 2016-11-30
- Cited by
- 1,749
- References
- 49
- Access
- Open access
- OpenAlex
- https://openalex.org/W2558580397
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:7507210
Keywords
Pascal (unit), Computer science, Residual, Segmentation, Artificial intelligence
References
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
- Rectified Linear Units Improve Restricted Boltzmann Machines
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Learning Deconvolution Network for Semantic Segmentation
- Fully convolutional networks for semantic segmentation
- The Pascal Visual Object Classes Challenge: A Retrospective
- Dropout: a simple way to prevent neural networks from overfitting
- Learning long-term dependencies with gradient descent is difficult
- ImageNet Large Scale Visual Recognition Challenge
- Conditional Random Fields as Recurrent Neural Networks
- The Role of Context for Object Detection and Semantic Segmentation in the Wild
- Semantic contours from inverse detectors
- ImageNet classification with deep convolutional neural networks
- MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
- Deep Residual Learning for Image Recognition
- Instance-Aware Semantic Segmentation via Multi-task Network Cascades
- Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
- Exploring Context with Deep Structured Models for Semantic Segmentation
- The Cityscapes Dataset for Semantic Urban Scene Understanding
Cited by
- Semantic Understanding of Scenes Through the ADE20K Dataset
- MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving
- Detecting unexpected obstacles for self-driving cars: Fusing deep learning and geometric modeling
- Sharing Residual Units Through Collective Tensor Factorization in Deep Neural Networks
- Automatic Skin Lesion Analysis using Large-scale Dermoscopy Images and Deep Residual Networks
- Multi-view deep learning for consistent semantic mapping with RGB-D cameras
- A Good Practice Towards Top Performance of Face Recognition: Transferred Deep Feature Fusion
- Automatic Liver Lesion Detection using Cascaded Deep Residual Networks
- Building Emotional Machines: Recognizing Image Emotions Through Deep Neural Networks
- Dynamic Steerable Blocks in Deep Residual Networks
- Survey of recent progress in semantic image segmentation with CNNs
- Improving Deep Learning Image Recognition Performance Using Region of Interest Localization Networks
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Online Adaptation of Convolutional Neural Networks for Video Object Segmentation
- A Review of Neural Network based Semantic Segmentation for Scene Understanding in Context of the self driving Car
- Data-Driven Sparse Structure Selection for Deep Neural Networks
- Deep Convolutional Neural Networks with Merge-and-Run Mappings
- Pathological OCT Retinal Layer Segmentation Using Branch Residual U-Shape Networks
- Residual Conv-Deconv Grid Network for Semantic Segmentation
- Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
Related papers
- Depth-Specific Variational Scaling Method to Improve Accuracy of ResNet
- Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
- Residual network with dense block
- Densely Connected Residual Network for Attack Recognition
- An improved residual network model for image recognition using a combination of snapshot ensembles and the cutout technique
- An Effective Deep Embedding Learning Method Based on Dense-Residual Networks for Speaker Verification