Distributed Convolutional Neural Networks for Object Recognition
This addresses object detection in complex backgrounds for computer vision applications, but appears incremental as it builds on existing CNN architectures with a novel loss function.
The paper tackles the problem of object recognition by proposing a distributed convolutional neural network (DisCNN) that focuses on extracting features for only a specific positive class, mapping positive samples to a compact set and negative samples to the origin. The model demonstrates excellent generalization on test data and remains effective for unseen classes.
This paper proposes a novel loss function for training a distributed convolutional neural network (DisCNN) to recognize only a specific positive class. By mapping positive samples to a compact set in high-dimensional space and negative samples to Origin, the DisCNN extracts only the features of the positive class. An experiment is given to prove this. Thus, the features of the positive class are disentangled from those of the negative classes. The model has a lightweight architecture because only a few positive-class features need to be extracted. The model demonstrates excellent generalization on the test data and remains effective even for unseen classes. Finally, using DisCNN, object detection of positive samples embedded in a large and complex background is straightforward.