In this paper, we present and discuss a deep mixture model with online knowledge distillation (MOD) for large-scale video temporal concept localization, which is ranked 3rd in the 3rd YouTube-8M Video Understanding Challenge. Specifically, we find that by enabling knowledge sharing with online distillation, fintuning a mixture model on a smaller dataset can achieve better evaluation performance. Based on this observation, in our final solution, we trained and fintuned 12 NeXtVLAD models in parallel with a 2-layer online distillation structure. The experimental results show that the proposed distillation structure can effectively avoid overfitting and shows superior generalization performance. The code is publicly available at: https://github.com/linrongc/solution_youtube8m_v3
@article{arxiv.1910.12295,
title = {MOD: A Deep Mixture Model with Online Knowledge Distillation for Large Scale Video Temporal Concept Localization},
author = {Rongcheng Lin and Jing Xiao and Jianping Fan},
journal= {arXiv preprint arXiv:1910.12295},
year = {2019}
}