A lookup table that stores precomputed outputs of the per-point MLP can replace network inference in point-wise point cloud models, achieving near-identical accuracy with much lower CPU latency.
Justlookup: One Millisecond Deep Feature Extraction for Point Clouds By Lookup Tables
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Deep models are capable of fitting complex high dimensional functions while usually yielding large computation load. There is no way to speed up the inference process by classical lookup tables due to the high-dimensional input and limited memory size. Recently, a novel architecture (PointNet) for point clouds has demonstrated that it is possible to obtain a complicated deep function from a set of 3-variable functions. In this paper, we exploit this property and apply a lookup table to encode these 3-variable functions. This method ensures that the inference time is only determined by the memory access no matter how complicated the deep function is. We conduct extensive experiments on ModelNet and ShapeNet datasets and demonstrate that we can complete the inference process in 1.5 ms on an Intel i7-8700 CPU (single core mode), 32x speedup over the PointNet architecture without any performance degradation.
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Justlookup: One Millisecond Deep Feature Extraction for Point Clouds By Lookup Tables
A lookup table that stores precomputed outputs of the per-point MLP can replace network inference in point-wise point cloud models, achieving near-identical accuracy with much lower CPU latency.