DVFL-Net, a 22M-parameter distilled video model, reaches near-teacher accuracy on five action recognition benchmarks with 27 GFLOPs, but its claimed state-of-the-art status is not fully supported by the reported numbers.
Preserve Pre-trained Knowledge: Transfer Learning With Self-Distillation For Action Recognition
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Video-based action recognition is one of the most popular topics in computer vision. With recent advances of selfsupervised video representation learning approaches, action recognition usually follows a two-stage training framework, i.e., self-supervised pre-training on large-scale unlabeled sets and transfer learning on a downstream labeled set. However, catastrophic forgetting of the pre-trained knowledge becomes the main issue in the downstream transfer learning of action recognition, resulting in a sub-optimal solution. In this paper, to alleviate the above issue, we propose a novel transfer learning approach that combines self-distillation in fine-tuning to preserve knowledge from the pre-trained model learned from the large-scale dataset. Specifically, we fix the encoder from the last epoch as the teacher model to guide the training of the encoder from the current epoch in the transfer learning. With such a simple yet effective learning strategy, we outperform state-of-the-art methods on widely used UCF101 and HMDB51 datasets in action recognition task.
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition
DVFL-Net, a 22M-parameter distilled video model, reaches near-teacher accuracy on five action recognition benchmarks with 27 GFLOPs, but its claimed state-of-the-art status is not fully supported by the reported numbers.