Tiny ImageNet Visual Recognition Challenge
Explore this paper's citation graph
Summary
This work investigates the effect of convolutional network depth, receptive field size, dropout layers, rectified activation unit type and dataset noise on its accuracy in Tiny-ImageNet Challenge settings and achieves excellent performance even compared to state-of-the-art results.
- Published
- 2015-01-01
- Cited by
- 3,106
- References
- 20
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:16664790
References
- Regularization of Neural Networks using DropConnect
- 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
- Some Improvements on Deep Convolutional Neural Network Based Image Classification
- Improving neural networks by preventing co-adaptation of feature detectors
- Return of the Devil in the Details: Delving Deep into Convolutional Nets
- On rectified linear units for speech processing
- Dropout: a simple way to prevent neural networks from overfitting
- Going deeper with convolutions
- Compete to Compute
- ImageNet: A large-scale hierarchical image database
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- ImageNet Large Scale Visual Recognition Challenge
- Caffe: Convolutional Architecture for Fast Feature Embedding
- ImageNet classification with deep convolutional neural networks
- Maxout Networks
- OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
- Rectifier Nonlinearities Improve Neural Network Acoustic Models
- Visualizing and Understanding Convolutional Networks
Cited by
- SGDR: Stochastic Gradient Descent with Warm Restarts
- A PID Controller Approach for Stochastic Optimization of Deep Networks
- On layer-level control of DNN training and its impact on generalization
- Recent Advances in Open Set Recognition: A Survey
- Stacking-Based Deep Neural Network: Deep Analytic Network for Pattern Classification
- On Implicit Filter Level Sparsity in Convolutional Neural Networks
- Deep Anomaly Detection with Outlier Exposure
- Using Pre-Training Can Improve Model Robustness and Uncertainty
- Incremental Learning with Maximum Entropy Regularization: Rethinking Forgetting and Intransigence
- Out-domain examples for generative models
- Deep CNN-based Multi-task Learning for Open-Set Recognition
- A Learnable Scatternet: Locally Invariant Convolutional Layers
- C2AE: Class Conditioned Auto-Encoder for Open-Set Recognition
- An Improved Deep Neural Network for Classification of Plant Seedling Images
- Differentiable Neural Architecture Search via Proximal Iterations
- Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
- On the Convex Behavior of Deep Neural Networks in Relation to the Layers' Width
- Relational Knowledge Distillation
- Highlight Every Step: Knowledge Distillation via Collaborative Teaching
- Continual Learning by Asymmetric Loss Approximation With Single-Side Overestimation
Related papers
No related papers recorded.