Multi-Fiber Networks for Video Recognition
arXiv:1807.11195
Abstract
In this paper, we aim to reduce the computational cost of spatio-temporal deep neural networks, making them run as fast as their 2D counterparts while preserving state-of-the-art accuracy on video recognition benchmarks. To this end, we present the novel Multi-Fiber architecture that slices a complex neural network into an ensemble of lightweight networks or fibers that run through the network. To facilitate information flow between fibers we further incorporate multiplexer modules and end up with an architecture that reduces the computational cost of 3D networks by an order of magnitude, while increasing recognition performance at the same time. Extensive experimental results show that our multi-fiber architecture significantly boosts the efficiency of existing convolution networks for both image and video recognition tasks, achieving state-of-the-art performance on UCF-101, HMDB-51 and Kinetics datasets. Our proposed model requires over 9x and 13x less computations than the I3D and R(2+1)D models, respectively, yet providing higher accuracy.
ECCV 2018, Code is on GitHub
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- The Kinetics Human Action Video Dataset
- Going Deeper with Convolutions
- ConvNet Architecture Search for Spatiotemporal Feature Learning
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
- A Closer Look at Spatiotemporal Convolutions for Action Recognition
- MaskConnect: Connectivity Learning by Gradient Descent
- Appearance-and-Relation Networks for Video Classification
- Dual Path Networks