The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction

Anh Thai, Stefan Stojanov, Zixuan Huang, James M. Rehg

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Continual learning has been extensively studied for classification tasks with methods developed to primarily avoid catastrophic forgetting, a phenomenon where earlier learned concepts are forgotten at the expense of more recent samples. In this work, we present a set of continual 3D object shape reconstruction tasks, including complete 3D shape reconstruction from different input modalities, as well as visible surface (2.5D) reconstruction which, surprisingly demonstrate positive knowledge (backward and forward) transfer when training with solely standard SGD and without additional heuristics. We provide evidence that continuously updated representation learning of single-view 3D shape reconstruction improves the performance on learned and novel categories over time. We provide a novel analysis of knowledge transfer ability by looking at the output distribution shift across sequential learning tasks. Finally, we show that the robustness of these tasks leads to the potential of having a proxy representation learning task for continual classification. The codebase, dataset and pretrained models released with this article can be found at https://github.com/rehg-lab/CLRec

Original languageEnglish (US)
Title of host publicationProceedings - 2022 International Conference on 3D Vision, 3DV 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages209-218
Number of pages10
ISBN (Electronic)9781665456708
DOIs
StatePublished - 2022
Externally publishedYes
Event10th International Conference on 3D Vision, 3DV 2022 - Prague, Czech Republic
Duration: Sep 12 2022Sep 15 2022

Publication series

NameProceedings - 2022 International Conference on 3D Vision, 3DV 2022

Conference

Conference10th International Conference on 3D Vision, 3DV 2022
Country/TerritoryCzech Republic
CityPrague
Period9/12/229/15/22

Keywords

  • 3D Shape Reconstruction
  • Continual Learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint

Dive into the research topics of 'The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction'. Together they form a unique fingerprint.

Cite this