Feature Evaluation of Deep Convolutional Neural Networks for Object Recognition and Detection
This work addresses feature evaluation in CNNs for computer vision tasks, but it is incremental as it builds on existing architectures like AlexNet and VGGNet.
The paper tackles the problem of evaluating convolutional neural network features for object recognition and detection by assessing additional convolutional layers beyond the commonly used fully connected layers, with experiments on Caltech 101 and Daimler Pedestrian Benchmark Datasets showing improved performance through feature concatenation and transformation.
In this paper, we evaluate convolutional neural network (CNN) features using the AlexNet architecture and very deep convolutional network (VGGNet) architecture. To date, most CNN researchers have employed the last layers before output, which were extracted from the fully connected feature layers. However, since it is unlikely that feature representation effectiveness is dependent on the problem, this study evaluates additional convolutional layers that are adjacent to fully connected layers, in addition to executing simple tuning for feature concatenation (e.g., layer 3 + layer 5 + layer 7) and transformation, using tools such as principal component analysis. In our experiments, we carried out detection and classification tasks using the Caltech 101 and Daimler Pedestrian Benchmark Datasets.