Training Data Generating Networks: Shape Reconstruction via Bi-level Optimization

Biao Zhang · Peter Wonka

Keywords: [ few-shot learning ] [ meta learning ] [ differentiable optimization ]

[ Abstract ]
[ Visit Poster at Spot F3 in Virtual World ] [ OpenReview
Thu 28 Apr 2:30 a.m. PDT — 4:30 a.m. PDT


We propose a novel 3d shape representation for 3d shape reconstruction from a single image. Rather than predicting a shape directly, we train a network to generate a training set which will be fed into another learning algorithm to define the shape. The nested optimization problem can be modeled by bi-level optimization. Specifically, the algorithms for bi-level optimization are also being used in meta learning approaches for few-shot learning. Our framework establishes a link between 3D shape analysis and few-shot learning. We combine training data generating networks with bi-level optimization algorithms to obtain a complete framework for which all components can be jointly trained. We improve upon recent work on standard benchmarks for 3d shape reconstruction.

Chat is not available.