用自回归模型做卷积核填充，提升卫星图像超分精度
Per-channel autoregressive linear prediction padding in tiled CNN processing of 2D spatial data
- 为每通道拟合自回归模型，用期望值生成可微填充
- 相比零填充和复制填充，均方误差降低，时间开销略增
- 适合卫星图像等高阶结构数据的超分辨率任务
我们提出一种可微的线性预测填充方法。对每个通道，通过最小化噪声项的平方和，拟合一个随机自回归线性模型于填充输入；填充值由已知像素给定条件下的模型期望值生成。在卫星图像数据上从头训练卷积型RVSR超分辨率模型，使用不同填充方式。线性预测填充相比零填充和复制填充，略微降低了平均平方超分误差，时间成本适度增加。该方法对卫星图像数据和RVSR特征图数据的逼近效果更优；零填充下，模型需动用更多容量补偿高近似误差。裁剪网络输出几像素可进一步降低超分误差，并减弱填充方式对误差的影响，因此对于本研究工作负载，推荐采用更快的复制或零填充配合输出裁剪。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。