paper-with-me

홈 › Papers

Generalization to Out-of-Distribution transformations

2021-09-29 · Shanka Subhra Mondal, Zack Dulberg, Jonathan Cohen

Humans understand a set of canonical geometric transformations (such as translation, rotation and scaling) that support generalization by being untethered to any specific object. We explored inductive biases that allowed artificial neural networks to learn these transformations in pixel space in a way that could generalize out-of-distribution (OOD). Unsurprisingly, we found that convolution and high training diversity were important contributing factors to OOD generalization of translation to untrained shapes, sizes, time-points and locations, however these weren’t sufficient for rotation and scaling. To remedy this we show that two more principle components are needed 1) iterative training where outputs are fed back as inputs 2) applying convolutions after conversion to log-polar space. We propose POLARAE which exploits all four components and outperforms standard convolutional autoencoders and variational autoencoders trained iteratively with high diversity wrt OOD generalization to larger shapes in larger grids and new locations.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityTranslation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Out-of-distribution Generalization with Causal Invariant Transformations

2022-03-22 · CVPR 2022 1 · Ruoyu Wang, Mingyang Yi, Zhitang Chen, Shengyu Zhu

In real-world applications, it is important and desirable to learn a model that performs well on out-of-distribution (OOD) data. Recently, causality has become a powerful tool to tackle the OOD generalization problem, wi…

Out-of-Distribution Generalization

Domain Generalization In Robust Invariant Representation

2023-04-07 · Gauri Gupta, Ritvik Kapila, Keshav Gupta, Ramesh Raskar

Unsupervised approaches for learning representations invariant to common transformations are used quite often for object recognition. Learning invariances makes models more robust and practical to use in real-world scena…

Domain GeneralizationObject Recognition

GIT: Detecting Uncertainty, Out-Of-Distribution and Adversarial Samples using Gradients and Invariance Transformations

2023-07-05 · Julia Lust, Alexandru P. Condurache

Deep neural networks tend to make overconfident predictions and often require additional detectors for misclassifications, particularly for safety-critical applications. Existing detection methods usually only focus on a…

Domain Generalization by Rejecting Extreme Augmentations

2023-10-10 · Masih Aminbeidokhti, Fidel A. Guerrero Peña, Heitor Rapela Medeiros, Thomas Dubail 외

Data augmentation is one of the most effective techniques for regularizing deep learning models and improving their recognition performance in a variety of tasks and domains. However, this holds for standard in-domain se…

Data AugmentationDomain Generalization

Improving OOD Generalization with Causal Invariant Transformations

2021-09-29 · Ruoyu Wang, Mingyang Yi, Shengyu Zhu, Zhitang Chen

In real-world applications, it is important and desirable to learn a model that performs well on out-of-distribution (OOD) data. Recently, causality has become a powerful tool to tackle the OOD generalization problem, wi…