Abstract: This paper presents a conceptually general and modularized neural collaborative network (NCN), which overcomes the limitations of the traditional convolutional neural networks (CNNs) in several aspects. Firstly, our NCN can directly handle non-Euclidean data without any pre-processing (e.g., graph normalizations) by defining a simple yet basic unit named neuron array for feature representation. Secondly, our NCN is capable of achieving both rotational equivariance and invariance properties via a simple yet powerful neuron collaboration mechanism, which imposes a ``glocal'' operation to capture both global and local information among neuron arrays within each layer. Thirdly, compared to the state-of-the-art networks that using large CNN kernels, our NCN with considerably fewer parameters can also achieve their strengths in feature learning by only exploiting highly efficient 1x1 convolution operations. Extensive experimental analyses on learning feature representation, handling novel viewpoints, and handling non-euclidean data demonstrate that our NCN can not only achieve state-of-the-art performance but also overcome the limitation of the conventional CNNs. The source codes will be released to facilite future researches after the review period for ensuring the anonymity.
Keywords: deep learning, neural architecture search, collaboration representation learning
1 Reply
Loading