paper-with-me

Papers

Learning Canonical Transformations

2020-11-17 · Zachary Dulberg, Jonathan Cohen

Humans understand a set of canonical geometric transformations (such as translation and rotation) that support generalization by being untethered to any specific object. We explore inductive biases that help a neural network model learn these transformations in pixel space in a way that can generalize out-of-domain. Specifically, we find that high training set diversity is sufficient for the extrapolation of translation to unseen shapes and scales, and that an iterative training scheme achieves significant extrapolation of rotation in time.

📄 PDF Abstract BibTeX arXiv:2011.08822

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityTranslation

Similar Papers 제목 키워드 기반

Deep Canonically Correlated LSTMs

2018-01-16 · Neil Mallinar, Corbin Rosset

We examine Deep Canonically Correlated LSTMs as a way to learn nonlinear transformations of variable length sequences and embed them into a correlated, fixed dimensional space. We use LSTMs to transform multi-view time-s…

Time SeriesTime Series Analysis

Neural Canonical Transformation with Symplectic Flows

2019-09-30 · Shuo-Hui Li, Chen-Xiao Dong, Linfeng Zhang, Lei Wang

Canonical transformation plays a fundamental role in simplifying and solving classical Hamiltonian systems. We construct flexible and powerful canonical transformations as generative models using symplectic neural networ…

Density Estimation

Zero-Shot Test-Time Canonicalization using Out-of-Distribution Scoring

2026-06-23 · Dominik Lindner, Johann Schmidt, Tom Siegl, Martin Becker 외 arxiv

Pretrained vision models often misclassify inputs that are rotated, scaled, or sheared, even though these affine transformations leave the object class unchanged. Robustness is usually restored either by building equivar…

Point Clouds

Test-Time Canonicalization by Foundation Models for Robust Perception

2025-07-14 · Utkarsh Singhal, Ryan Feng, Stella X. Yu, Atul Prakash

Real-world visual perception requires invariance to diverse transformations, yet current methods rely heavily on specialized architectures or training on predefined augmentations, limiting generalization. We propose FOCA…

Representation Learning Through Latent Canonicalizations

2020-02-26 · Or Litany, Ari Morcos, Srinath Sridhar, Leonidas Guibas 외

We seek to learn a representation on a large annotated data source that generalizes to a target domain using limited new supervision. Many prior approaches to this problem have focused on learning "disentangled" represen…

DisentanglementRepresentation Learning