RecNets: Channel-wise Recurrent Convolutional Neural Networks
This addresses the need for efficient models in resource-constrained environments, though it is incremental as it builds on existing compact architecture ideas.
The paper tackles the problem of designing compact neural network architectures for computer vision by introducing Channel-wise recurrent convolutional neural networks (RecNets), which use recurrent processing to reduce parameters while maintaining accuracy, achieving superior size-accuracy trade-offs on CIFAR-10 and CIFAR-100 benchmarks.
In this paper, we introduce Channel-wise recurrent convolutional neural networks (RecNets), a family of novel, compact neural network architectures for computer vision tasks inspired by recurrent neural networks (RNNs). RecNets build upon Channel-wise recurrent convolutional (CRC) layers, a novel type of convolutional layer that splits the input channels into disjoint segments and processes them in a recurrent fashion. In this way, we simulate wide, yet compact models, since the number of parameters is vastly reduced via the parameter sharing of the RNN formulation. Experimental results on the CIFAR-10 and CIFAR-100 image classification tasks demonstrate the superior size-accuracy trade-off of RecNets compared to other compact state-of-the-art architectures.