# Low-memory convolutional neural networks through incremental depth-first processing

arXiv: https://arxiv.org/abs/1804.10727 · HTML: https://mlsanity.com/paper/1804.10727/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2018.

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

- [On-Sensor Convolutional Neural Networks with Early-Exits](https://mlsanity.com/paper/2503.16939/) (2025)

## Abstract (arXiv)

We introduce an incremental processing scheme for convolutional neural network (CNN) inference, targeted at embedded applications with limited memory budgets. Instead of processing layers one by one, individual input pixels are propagated through all parts of the network they can influence under the given structural constraints. This depth-first updating scheme comes with hard bounds on the memory footprint: the memory required is constant in the case of 1D input and proportional to the square root of the input dimension in the case of 2D input.