# CBinfer: Change-Based Inference for Convolutional Neural Networks on Video Data

arXiv: https://arxiv.org/abs/1704.04313 · HTML: https://mlsanity.com/paper/1704.04313/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2017.

## Built on by (most cited first, 8 of 8)

- [Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers](https://mlsanity.com/paper/2308.13494/) (2023)
- [Boosting Mobile CNN Inference through Semantic Memory](https://mlsanity.com/paper/2112.02644/) (2021)
- [Survey: Exploiting Data Redundancy for Optimization of Deep Learning](https://mlsanity.com/paper/2208.13363/) (2022)
- [MaskVD: Region Masking for Efficient Video Object Detection](https://mlsanity.com/paper/2407.12067/) (2024)
- [A Construction Kit for Efficient Low Power Neural Network Accelerator Designs](https://mlsanity.com/paper/2106.12810/) (2021)
- [Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs](https://mlsanity.com/paper/2307.14988/) (2023)
- [SparseTem: Boosting the Efficiency of CNN-Based Video Encoders by Exploiting Temporal Continuity](https://mlsanity.com/paper/2410.20790/) (2024)
- [evMLP: An Efficient Event-Driven MLP Architecture for Vision](https://mlsanity.com/paper/2507.01927/) (2025)

## Abstract (arXiv)

Extracting per-frame features using convolutional neural networks for real-time processing of video data is currently mainly performed on powerful GPU-accelerated workstations and compute clusters. However, there are many applications such as smart surveillance cameras that require or would benefit from on-site processing. To this end, we propose and evaluate a novel algorithm for change-based evaluation of CNNs for video data recorded with a static camera setting, exploiting the spatio-temporal sparsity of pixel changes. We achieve an average speed-up of 8.6x over a cuDNN baseline on a realistic benchmark with a negligible accuracy loss of less than 0.1% and no retraining of the network. The resulting energy efficiency is 10x higher than that of per-frame evaluation and reaches an equivalent of 328 GOp/s/W on the Tegra X1 platform.