Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledge
arXiv:2004.00176
Abstract
Cross-modal knowledge distillation deals with transferring knowledge from a model trained with superior modalities (Teacher) to another model trained with weak modalities (Student). Existing approaches require paired training examples exist in both modalities. However, accessing the data from superior modalities may not always be feasible. For example, in the case of 3D hand pose estimation, depth maps, point clouds, or stereo images usually capture better hand structures than RGB images, but most of them are expensive to be collected. In this paper, we propose a novel scheme to train the Student in a Target dataset where the Teacher is unavailable. Our key idea is to generalize the distilled cross-modal knowledge learned from a Source dataset, which contains paired examples from both modalities, to the Target dataset by modeling knowledge as priors on parameters of the Student. We name our method "Cross-Modal Knowledge Generalization" and demonstrate that our scheme results in competitive performance for 3D hand pose estimation on standard benchmark datasets.
arXiv commentIn CVPR 2020. (15 pages including supplementary material)
References in corpus (10)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Distilling the Knowledge in a Neural Network
- Prototypical Networks for Few-shot Learning
- Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
- Do Deep Nets Really Need to be Deep?
- Embodied Hands: Modeling and Capturing Hands and Bodies Together
- Learning from Synthetic Humans
- A Simple Neural Attentive Meta-Learner
- Knowledge Transfer with Jacobian Matching
- Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention