English

What Makes Training Multi-Modal Classification Networks Hard?

Computer Vision and Pattern Recognition 2020-04-06 v5 Machine Learning

Abstract

Consider end-to-end training of a multi-modal vs. a single-modal network on a task with multiple input modalities: the multi-modal network receives more information, so it should match or outperform its single-modal counterpart. In our experiments, however, we observe the opposite: the best single-modal network always outperforms the multi-modal network. This observation is consistent across different combinations of modalities and on different tasks and benchmarks. This paper identifies two main causes for this performance drop: first, multi-modal networks are often prone to overfitting due to increased capacity. Second, different modalities overfit and generalize at different rates, so training them jointly with a single optimization strategy is sub-optimal. We address these two problems with a technique we call Gradient Blending, which computes an optimal blend of modalities based on their overfitting behavior. We demonstrate that Gradient Blending outperforms widely-used baselines for avoiding overfitting and achieves state-of-the-art accuracy on various tasks including human action recognition, ego-centric action recognition, and acoustic event detection.

Keywords

Cite

@article{arxiv.1905.12681,
  title  = {What Makes Training Multi-Modal Classification Networks Hard?},
  author = {Weiyao Wang and Du Tran and Matt Feiszli},
  journal= {arXiv preprint arXiv:1905.12681},
  year   = {2020}
}

Comments

CVPR 2020

R2 v1 2026-06-23T09:32:13.986Z