Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-Identification
arXiv:1705.09882
Abstract
We address the problem of person re-identification from commodity depth sensors. One challenge for depth-based recognition is data scarcity. Our first contribution addresses this problem by introducing split-rate RGB-to-Depth transfer, which leverages large RGB datasets more effectively than popular fine-tuning approaches. Our transfer scheme is based on the observation that the model parameters at the bottom layers of a deep convolutional neural network can be directly shared between RGB and depth data while the remaining layers need to be fine-tuned rapidly. Our second contribution enhances re-identification for video by implementing temporal attention as a Bernoulli-Sigmoid unit acting upon frame-level features. Since this unit is stochastic, the temporal attention parameters are trained using reinforcement learning. Extensive experiments validate the accuracy of our method in person re-identification from depth sequences. Finally, in a scenario where subjects wear unseen clothes, we show large performance gains compared to a state-of-the-art model which relies on RGB data.
arXiv comment19 pages, 7 figures, 2 tables
References in corpus (7)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Improving neural networks by preventing co-adaptation of feature detectors
- How transferable are features in deep neural networks?
- Recurrent Models of Visual Attention
- Learning to Execute
- Describing Videos by Exploiting Temporal Structure
- Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs