2023/05/10 by Benmeziane, Hadjer, Bouzidi, Halima, Ouarnoughi, Hamza +2
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
paper · doi:10.48550/arxiv.2305.06492
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.