# Treasure What You Have: Exploiting Similarity in Deep Neural Networks for Efficient Video Processing

arXiv: https://arxiv.org/abs/2305.06492 · HTML: https://mlsanity.com/paper/2305.06492/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 16 references that are in the map.
- First posted on arXiv 10 May 2023.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [The ApolloScape Open Dataset for Autonomous Driving and its Application](https://mlsanity.com/paper/1803.06184/) (2018)
- [Practical and Optimal LSH for Angular Distance](https://mlsanity.com/paper/1509.02897/) (2015)
- [HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers](https://mlsanity.com/paper/2211.08110/) (2022)
- [EVA2: Exploiting Temporal Redundancy in Live Computer Vision](https://mlsanity.com/paper/1803.06312/) (2018)
- [Expected Improvement versus Predicted Value in Surrogate-Based Optimization](https://mlsanity.com/paper/2001.02957/) (2020)

## Abstract (arXiv)

Deep learning has enabled various Internet of Things (IoT) applications. Still, designing models with high accuracy and computational efficiency remains a significant challenge, especially in real-time video processing applications. Such applications exhibit high inter- and intra-frame redundancy, allowing further improvement. This paper proposes a similarity-aware training methodology that exploits data redundancy in video frames for efficient processing. Our approach introduces a per-layer regularization that enhances computation reuse by increasing the similarity of weights during training. We validate our methodology on two critical real-time applications, lane detection and scene parsing. We observe an average compression ratio of approximately 50% and a speedup of ~ 1.5x for different models while maintaining the same accuracy.