Multimodal Distillation for Egocentric Action Recognition
This addresses the deployment complexity of multimodal models for egocentric video understanding, offering a practical solution for applications like robotics or AR, though it is incremental as it builds on existing distillation techniques.
The paper tackles the problem of deploying multimodal models for egocentric action recognition by using knowledge distillation to transfer performance from a multimodal teacher to a unimodal student that only uses RGB frames at inference, achieving higher accuracy and better calibration on Epic-Kitchens and Something-Something datasets.
The focal point of egocentric video understanding is modelling hand-object interactions. Standard models, e.g. CNNs or Vision Transformers, which receive RGB frames as input perform well. However, their performance improves further by employing additional input modalities that provide complementary cues, such as object detections, optical flow, audio, etc. The added complexity of the modality-specific modules, on the other hand, makes these models impractical for deployment. The goal of this work is to retain the performance of such a multimodal approach, while using only the RGB frames as input at inference time. We demonstrate that for egocentric action recognition on the Epic-Kitchens and the Something-Something datasets, students which are taught by multimodal teachers tend to be more accurate and better calibrated than architecturally equivalent models trained on ground truth labels in a unimodal or multimodal fashion. We further adopt a principled multimodal knowledge distillation framework, allowing us to deal with issues which occur when applying multimodal knowledge distillation in a naive manner. Lastly, we demonstrate the achieved reduction in computational complexity, and show that our approach maintains higher performance with the reduction of the number of input views. We release our code at https://github.com/gorjanradevski/multimodal-distillation.