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

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

18 Jan 2021arXiv:2101.07295archive 2025-07-28

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

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 pre-trained models released with this article can be found at https://github.com/rehg-lab/CLRec

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ngailapdi/CLRec officialmentioned in papermentioned on GitHubpytorch report
rehg-lab/CLRec officialmentioned in papermentioned on GitHubpytorch report
IsaacRe/dynamic-representation-tracking mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Shape ReconstructionContinual LearningRepresentation LearningTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections