# Latent Equivariant Operators for Robust Object Recognition: Promises and Challenges

arXiv: https://arxiv.org/abs/2602.18406 · HTML: https://mlsanity.com/paper/2602.18406/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 20 Feb 2026.

## Builds on (most cited first, 18 of 18)

- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [Towards a Definition of Disentangled Representations](https://mlsanity.com/paper/1812.02230/) (2018)
- [A General Theory of Equivariant CNNs on Homogeneous Spaces](https://mlsanity.com/paper/1811.02017/) (2018)
- [Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects](https://mlsanity.com/paper/1811.11553/) (2018)
- [B-Spline CNNs on Lie Groups](https://mlsanity.com/paper/1909.12057/) (2019)
- [When does dough become a bagel? Analyzing the remaining mistakes on ImageNet](https://mlsanity.com/paper/2205.04596/) (2022)
- [Equivariant Neural Rendering](https://mlsanity.com/paper/2006.07630/) (2020)
- [Emergent Equivariance in Deep Ensembles](https://mlsanity.com/paper/2403.03103/) (2024)
- [Representing Closed Transformation Paths in Encoded Network Latent Space](https://mlsanity.com/paper/1912.02644/) (2019)
- [The Robustness Limits of SoTA Vision Models to Natural Variation](https://mlsanity.com/paper/2210.13604/) (2022)
- [Addressing the Topological Defects of Disentanglement via Distributed Operators](https://mlsanity.com/paper/2102.05623/) (2021)
- [Progress and limitations of deep networks to recognize objects in unusual poses](https://mlsanity.com/paper/2207.08034/) (2022)
- [On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory](https://mlsanity.com/paper/2412.11521/) (2024)
- [A comparison between humans and AI at recognizing objects in unusual poses](https://mlsanity.com/paper/2402.03973/) (2024)
- [Learning Internal Representations of 3D Transformations from 2D Projected Inputs](https://mlsanity.com/paper/2303.17776/) (2023)
- [A Deep Learning Model of Mental Rotation Informed by Interactive VR Experiments](https://mlsanity.com/paper/2512.13517/) (2025)

## Abstract (arXiv)

Despite the successes of deep learning in computer vision, difficulties persist in recognizing objects that have undergone group-symmetric transformations rarely seen during trainingunicodex2013for example objects seen in unusual poses, scales, positions, or combinations thereof. Equivariant neural networks are a solution to the problem of generalizing across symmetric transformations, but require knowledge of transformations a priori. An alternative family of architectures proposes to learn equivariant operators in a latent space, from examples of symmetric transformations. Here, using simple datasets of rotated and translated noisy MNIST, we illustrate how such architectures can successfully be harnessed for out-of-distribution classification, thus overcoming the limitations of both traditional and equivariant networks. While conceptually enticing, we discuss challenges ahead on the path of scaling these architectures to more complex datasets. Our code is available at https://github.com/BRAIN-Aalto/equivariantoperator.