Training Data Generating Networks: Linking 3D Shapes and Few-Shot Classification

Biao Zhang, Peter Wonka

Keywords: shape representation, single image 3d reconstruction, few-shot learning, meta learning

Abstract:

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 feed into another learning algorithm to define the shape.
Training data generating networks establish a link between few-shot learning and 3d shape analysis. We propose a novel meta-learning framework to jointly train the data generating network and other components. We improve upon recent work on standard benchmarks for 3d shape reconstruction, but our novel shape representation has many applications.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=yJ-BEw8lhN