Object Detection Based on Distributed Convolutional Neural Networks
This work addresses object detection for computer vision applications, but it appears incremental as it builds on existing DisCNN frameworks without introducing major new paradigms.
The paper tackles object detection by proposing a method based on Distributed Convolutional Neural Networks (DisCNN), where high-scoring patches across scales are overlapped to form bounding boxes, resulting in accelerated detection due to parallel processing and a lightweight architecture.
Based on the Distributed Convolutional Neural Network(DisCNN), a straightforward object detection method is proposed. The modules of the output vector of a DisCNN with respect to a specific positive class are positively monotonic with the presence probabilities of the positive features. So, by identifying all high-scoring patches across all possible scales, the positive object can be detected by overlapping them to form a bounding box. The essential idea is that the object is detected by detecting its features on multiple scales, ranging from specific sub-features to abstract features composed of these sub-features. Training DisCNN requires only object-centered image data with positive and negative class labels. The detection process for multiple positive classes can be conducted in parallel to significantly accelerate it, and also faster for single-object detection because of its lightweight model architecture.