Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
7-2021
Abstract
It is not trivial to optimally learn a 3D Convolutional Neural Networks (3D ConvNets) due to high complexity and various options of the training scheme. The most common hand-tuning process starts from learning 3D ConvNets using short video clips and then is followed by learning long-term temporal dependency using lengthy clips, while gradually decaying the learning rate from high to low as training progresses. The fact that such process comes along with several heuristic settings motivates the study to seek an optimal "path" to automate the entire training. In this paper, we decompose the path into a series of training "states" and specify the hyper-parameters, e.g., learning rate and the length of input clips, in each state. The estimation of the knee point on the performance-epoch curve triggers the transition from one state to another. We perform dynamic programming over all the candidate states to plan the optimal permutation of states, i.e., optimization path. Furthermore, we devise a new 3D ConvNets with a unique design of dual-head classifier to improve spatial and temporal discrimination. Extensive experiments on seven public video recognition benchmarks demonstrate the advantages of our proposal. With the optimization planning, our 3D ConvNets achieves superior results when comparing to the state-of-the-art recognition methods. More remarkably, we obtain the top-1 accuracy of 80.5% and 82.7% on Kinetics-400 and Kinetics-600 datasets, respectively.
Discipline
OS and Networks
Research Areas
Software and Cyber-Physical Systems
Publication
Proceedings of the 38th International Conference on Machine Learning, Virtual Conference, 2021 July 18-24
Volume
139
First Page
8726
Last Page
8736
Publisher
PMLR
City or Country
Virtual Conference
Citation
QIU, Zhaofan; YAO, Ting; NGO, Chong-wah; and MEI, Tao.
Optimization planning for 3D ConvNets. (2021). Proceedings of the 38th International Conference on Machine Learning, Virtual Conference, 2021 July 18-24. 139, 8726-8736.
Available at: https://ink.library.smu.edu.sg/sis_research/6728
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.