Unsupervised Learning Layers for Video Analysis
This work addresses the problem of label-free video analysis for researchers and practitioners, offering a method that can be used in unsupervised or semi-supervised settings, but it appears incremental as it builds on existing neural network layers.
The paper tackles unsupervised video analysis by introducing two unsupervised learning layers that serve as cost functions and provide local training signals, enabling extraction of shape and motion features from videos. Experiments on synthetic and real-world videos showed these layers can be applied to tasks like head orientation estimation and moving object localization.
This paper presents two unsupervised learning layers (UL layers) for label-free video analysis: one for fully connected layers, and the other for convolutional ones. The proposed UL layers can play two roles: they can be the cost function layer for providing global training signal; meanwhile they can be added to any regular neural network layers for providing local training signals and combined with the training signals backpropagated from upper layers for extracting both slow and fast changing features at layers of different depths. Therefore, the UL layers can be used in either pure unsupervised or semi-supervised settings. Both a closed-form solution and an online learning algorithm for two UL layers are provided. Experiments with unlabeled synthetic and real-world videos demonstrated that the neural networks equipped with UL layers and trained with the proposed online learning algorithm can extract shape and motion information from video sequences of moving objects. The experiments demonstrated the potential applications of UL layers and online learning algorithm to head orientation estimation and moving object localization.