Deeply-Fused Nets

Abstract

In this paper, we present a novel deep learning approach, deeply-fused nets. The central idea of our approach is deep fusion, i.e., combine the intermediate representations of base networks, where the fused output serves as the input of the remaining part of each base network, and perform such combinations deeply over several intermediate representations. The resulting deeply fused net enjoys several benefits. First, it is able to learn multi-scale representations as it enjoys the benefits of more base networks, which could form the same fused network, other than the initial group of base networks. Second, in our suggested fused net formed by one deep and one shallow base networks, the flows of the information from the earlier intermediate layer of the deep base network to the output and from the input to the later intermediate layer of the deep base network are both improved. Last, the deep and shallow base networks are jointly learnt and can benefit from each other. More interestingly, the essential depth of a fused net composed from a deep base network and a shallow base network is reduced because the fused net could be composed from a less deep base network, and thus training the fused net is less difficult than training the initial deep base network. Empirical results demonstrate that our approach achieves superior performance over two closely-related methods, ResNet and Highway, and competitive performance compared to the state-of-the-arts.

Cited by in corpus (14)

• Densely Connected Convolutional Networks
• Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges
• Deep High-Resolution Representation Learning for Visual Recognition
• Multi-View 3D Object Detection Network for Autonomous Driving
• Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector
• Deep Convolutional Neural Networks with Merge-and-Run Mappings
• Training Shallow and Thin Networks for Acceleration via Knowledge Distillation with Conditional Adversarial Networks
• Fusing Bird View LIDAR Point Cloud and Front View Camera Image for Deep Object Detection
• Accelerating Deep Neural Networks with Spatial Bottleneck Modules
• Towards Learning Affine-Invariant Representations via Data-Efficient CNNs
• AOGNets: Compositional Grammatical Architectures for Deep Learning
• SORT: Second-Order Response Transform for Visual Recognition
• Deep Global-Connected Net With The Generalized Multi-Piecewise ReLU Activation in Deep Learning
• TRACER: A Framework for Facilitating Accurate and Interpretable Analytics for High Stakes Applications