Mimicking Ensemble Learning with Deep Branched Networks
This work addresses image classification for computer vision applications, but it is incremental as it builds on existing ensemble and residual network concepts.
The paper tackles image classification by proposing a branched residual network that mimics ensemble learning, achieving improved performance on the ImageNet task.
This paper proposes a branched residual network for image classification. It is known that high-level features of deep neural network are more representative than lower-level features. By sharing the low-level features, the network can allocate more memory to high-level features. The upper layers of our proposed network are branched, so that it mimics the ensemble learning. By mimicking ensemble learning with single network, we have achieved better performance on ImageNet classification task.