Distributed Convolutional Neural Networks for Object Recognition

TL;DR

This paper introduces a novel loss function for distributed CNNs that isolates positive class features, enabling efficient recognition and detection even in complex backgrounds, with strong generalization to unseen classes.

Contribution

The paper presents a new loss function and architecture for DisCNN that disentangles positive class features from negatives, improving recognition and detection in complex scenes.

Findings

Model achieves excellent generalization on test data.

Effective detection of positive samples in complex backgrounds.

Lightweight architecture with few positive-class features.

Abstract

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.