论文标题
HashenCoding:使用多尺度坐标哈希进行自动编码
HashEncoding: Autoencoding with Multiscale Coordinate Hashing
论文作者
论文摘要
我们提出了HashenCoding,这是一种新型的自动编码体系结构,利用非参数的多尺度坐标哈希函数来促进无需卷积的每个像素解码器。通过利用哈希函数的空间折叠行为,HashenCoding允许具有固有的多尺寸嵌入空间,该空间仍然比原始图像小得多。结果,与传统自动编码器中的解码器相比,解码器需要很少的参数,从而接近原始图像的非参数重建,并允许更大的通用性。最后,通过将反向传播直接传播到坐标空间中,我们表明可以利用载键编码来用于诸如光学流量之类的几何任务。
We present HashEncoding, a novel autoencoding architecture that leverages a non-parametric multiscale coordinate hash function to facilitate a per-pixel decoder without convolutions. By leveraging the space-folding behaviour of hashing functions, HashEncoding allows for an inherently multiscale embedding space that remains much smaller than the original image. As a result, the decoder requires very few parameters compared with decoders in traditional autoencoders, approaching a non-parametric reconstruction of the original image and allowing for greater generalizability. Finally, by allowing backpropagation directly to the coordinate space, we show that HashEncoding can be exploited for geometric tasks such as optical flow.