# Per-channel autoregressive linear prediction padding in tiled CNN processing of 2D spatial data

arXiv: https://arxiv.org/abs/2502.12300 · HTML: https://mlsanity.com/paper/2502.12300/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 11 references that are in the map.
- First posted on arXiv 17 Feb 2025.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Equinox: neural networks in JAX via callable PyTrees and filtered transformations](https://mlsanity.com/paper/2111.00254/) (2021)
- [NullHop: A Flexible Convolutional Neural Network Accelerator Based on Sparse Representations of Feature Maps](https://mlsanity.com/paper/1706.01406/) (2017)
- [Tiling and Stitching Segmentation Output for Remote Sensing: Basic Challenges and Recommendations](https://mlsanity.com/paper/1805.12219/) (2018)
- [Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey](https://mlsanity.com/paper/2404.16484/) (2024)
- [Padding-free Convolution based on Preservation of Differential Characteristics of Kernels](https://mlsanity.com/paper/2309.06370/) (2023)

## Abstract (arXiv)

We present linear prediction as a differentiable padding method. For each channel, a stochastic autoregressive linear model is fitted to the padding input by minimizing its noise terms in the least-squares sense. The padding is formed from the expected values of the autoregressive model given the known pixels. We trained the convolutional RVSR super-resolution model from scratch on satellite image data, using different padding methods. Linear prediction padding slightly reduced the mean square super-resolution error compared to zero and replication padding, with a moderate increase in time cost. Linear prediction padding better approximated satellite image data and RVSR feature map data. With zero padding, RVSR appeared to use more of its capacity to compensate for the high approximation error. Cropping the network output by a few pixels reduced the super-resolution error and the effect of the choice of padding method on the error, favoring output cropping with the faster replication and zero padding methods, for the studied workload.