COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers

TL;DR

COMEDIAN introduces a self-supervised and knowledge distillation-based pretraining pipeline for spatiotemporal transformers, significantly improving action spotting accuracy and convergence speed on SoccerNet-v2.

Contribution

It proposes a novel three-step pretraining pipeline combining self-supervised learning and knowledge distillation for action spotting with transformers.

Findings

Achieves state-of-the-art results on SoccerNet-v2.

Pretraining improves performance over non-pretrained models.

Faster convergence during training.

Abstract

We present COMEDIAN, a novel pipeline to initialize spatiotemporal transformers for action spotting, which involves self-supervised learning and knowledge distillation. Action spotting is a timestamp-level temporal action detection task. Our pipeline consists of three steps, with two initialization stages. First, we perform self-supervised initialization of a spatial transformer using short videos as input. Additionally, we initialize a temporal transformer that enhances the spatial transformer's outputs with global context through knowledge distillation from a pre-computed feature bank aligned with each short video segment. In the final step, we fine-tune the transformers to the action spotting task. The experiments, conducted on the SoccerNet-v2 dataset, demonstrate state-of-the-art performance and validate the effectiveness of COMEDIAN's pretraining paradigm. Our results highlight several advantages of our pretraining pipeline, including improved performance and faster convergence compared to non-pretrained models.