# MILA: Multi-Task Learning from Videos via Efficient Inter-Frame Attention

arXiv: https://arxiv.org/abs/2002.07362 · HTML: https://mlsanity.com/paper/2002.07362/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Feb 2020.

## Built on by (most cited first, 1 of 1)

- [Structured Pruning for Multi-Task Deep Neural Networks](https://mlsanity.com/paper/2304.06840/) (2023)

## Abstract (arXiv)

Prior work in multi-task learning has mainly focused on predictions on a single image. In this work, we present a new approach for multi-task learning from videos via efficient inter-frame local attention (MILA). Our approach contains a novel inter-frame attention module which allows learning of task-specific attention across frames. We embed the attention module in a ``slow-fast'' architecture, where the slower network runs on sparsely sampled keyframes and the light-weight shallow network runs on non-keyframes at a high frame rate. We also propose an effective adversarial learning strategy to encourage the slow and fast network to learn similar features. Our approach ensures low-latency multi-task learning while maintaining high quality predictions. Experiments show competitive accuracy compared to state-of-the-art on two multi-task learning benchmarks while reducing the number of floating point operations (FLOPs) by up to 70%. In addition, our attention based feature propagation method (ILA) outperforms prior work in terms of task accuracy while also reducing up to 90% of FLOPs.