Timezone: »

 
Poster
Meta-Learning Sparse Implicit Neural Representations
Jaeho Lee · Jihoon Tack · Namhoon Lee · Jinwoo Shin

Wed Dec 08 12:30 AM -- 02:00 AM (PST) @
in Poster Session 3 »

Implicit neural representations are a promising new avenue of representing general signals by learning a continuous function that, parameterized as a neural network, maps the domain of a signal to its codomain; the mapping from spatial coordinates of an image to its pixel values, for example. Being capable of conveying fine details in a high dimensional signal, unboundedly of its domain, implicit neural representations ensure many advantages over conventional discrete representations. However, the current approach is difficult to scale for a large number of signals or a data set, since learning a neural representation---which is parameter heavy by itself---for each signal individually requires a lot of memory and computations. To address this issue, we propose to leverage a meta-learning approach in combination with network compression under a sparsity constraint, such that it renders a well-initialized sparse parameterization that evolves quickly to represent a set of unseen signals in the subsequent training. We empirically demonstrate that meta-learned sparse neural representations achieve a much smaller loss than dense meta-learned models with the same number of parameters, when trained to fit each signal using the same number of optimization steps.

Keywords: Deep Learning · Optimization · Meta Learning · Representation Learning

Author Information

Jaeho Lee (KAIST)
Jihoon Tack (KAIST)
Namhoon Lee (University of Oxford)
Jinwoo Shin (KAIST)

More from the Same Authors