paper-with-me

Papers

Using and Abusing Equivariance

2023-08-22 · Tom Edixhoven, Attila Lengyel, Jan van Gemert

In this paper we show how Group Equivariant Convolutional Neural Networks use subsampling to learn to break equivariance to their symmetries. We focus on 2D rotations and reflections and investigate the impact of broken equivariance on network performance. We show that a change in the input dimension of a network as small as a single pixel can be enough for commonly used architectures to become approximately equivariant, rather than exactly. We investigate the impact of networks not being exactly equivariant and find that approximately equivariant networks generalise significantly worse to unseen symmetries compared to their exactly equivariant counterparts. However, when the symmetries in the training data are not identical to the symmetries of the network, we find that approximately equivariant networks are able to relax their own equivariant constraints, causing them to match or outperform exactly equivariant networks on common benchmark datasets.

📄 PDF Abstract BibTeX arXiv:2308.11316

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

TrollMeta@DravidianLangTech-EACL2021: Meme classification using deep learning

2021-04-01 · EACL (DravidianLangTech) 2021 4 · Manoj Balaji J, Chinmaya Hs

Memes act as a medium to carry one’s feelings, cultural ideas, or practices by means of symbols, imitations, or simply images. Whenever social media is involved, hurting the feelings of others and abusing others are alwa…

ClassificationDeep LearningMeme Classification

Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs

2023-07-19 · Eugene Bagdasaryan, Tsung-Yin Hsieh, Ben Nassi, Vitaly Shmatikov

We demonstrate how images and sounds can be used for indirect prompt and instruction injection in multi-modal LLMs. An attacker generates an adversarial perturbation corresponding to the prompt and blends it into an imag…

What Affects Learned Equivariance in Deep Image Recognition Models?

2023-04-05 · Robert-Jan Bruintjes, Tomasz Motyka, Jan van Gemert

Equivariance w.r.t. geometric transformations in neural networks improves data efficiency, parameter efficiency and robustness to out-of-domain perspective shifts. When equivariance is not designed into a neural network,…

Data AugmentationInductive BiasTranslation

Equivariance-aware Architectural Optimization of Neural Networks

2022-10-11 · Kaitlin Maile, Dennis G. Wilson, Patrick Forré

Incorporating equivariance to symmetry groups as a constraint during neural network training can improve performance and generalization for tasks exhibiting those symmetries, but such symmetries are often not perfectly n…

Neural Architecture Search

Relaxing Equivariance Constraints with Non-stationary Continuous Filters

2022-04-14 · Tycho F. A. van der Ouderaa, David W. Romero, Mark van der Wilk

Equivariances provide useful inductive biases in neural network modeling, with the translation equivariance of convolutional neural networks being a canonical example. Equivariances can be embedded in architectures throu…

image-classificationImage Classification