Multi-Fiber Networks for Video Recognition
This work addresses efficiency issues in video recognition for researchers and practitioners, offering a novel method to make 3D networks as fast as 2D ones without sacrificing accuracy.
The paper tackles the problem of high computational cost in spatio-temporal deep neural networks for video recognition by introducing the Multi-Fiber architecture, which reduces computational cost by over 9x and 13x compared to I3D and R(2+1)D models while achieving state-of-the-art accuracy on benchmarks like UCF-101, HMDB-51, and Kinetics.
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.