Feature Representation in Convolutional Neural Networks

Abstract

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.

References in corpus (2)

• Theano: new features and speed improvements
• Advances in Optimizing Recurrent Networks

Cited by in corpus (5)

• A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation
• Orbital instability of standing waves for NLS equation on Star Graphs
• DeepVA: Bridging Cognition and Computation through Semantic Interaction and Deep Learning
• Evaluating Semantic Interaction on Word Embeddings via Simulation
• Experimental Evaluation of Human Motion Prediction: Toward Safe and Efficient Human Robot Collaboration