Firerisk: A remote sensing dataset for fire risk assessment with benchmarks using supervised and self-supervised learning

S Shen, S Seneviratne, X Wanyan… - … Conference on Digital …, 2023 - ieeexplore.ieee.org
In recent decades, wildfires have caused tremendous property losses, fatalities, and
extensive damage to forest ecosystems. Inspired by the abundance of publicly available …

Steerers: A framework for rotation equivariant keypoint descriptors

G Bökman, J Edstedt, M Felsberg… - Proceedings of the …, 2024 - openaccess.thecvf.com
Image keypoint descriptions that are discriminative and matchable over large changes in
viewpoint are vital for 3D reconstruction. However descriptions output by learned descriptors …

Self-supervised learning of split invariant equivariant representations

Q Garrido, L Najman, Y Lecun - arXiv preprint arXiv:2302.10283, 2023 - arxiv.org
Recent progress has been made towards learning invariant or equivariant representations
with self-supervised learning. While invariant methods are evaluated on large scale …

The surprising effectiveness of equivariant models in domains with latent symmetry

D Wang, JY Park, N Sortur, LLS Wong… - arXiv preprint arXiv …, 2022 - arxiv.org
Extensive work has demonstrated that equivariant neural networks can significantly improve
sample efficiency and generalization by enforcing an inductive bias in the network …

A general theory of correct, incorrect, and extrinsic equivariance

D Wang, X Zhu, JY Park, M Jia, G Su… - Advances in …, 2024 - proceedings.neurips.cc
Although equivariant machine learning has proven effective at many tasks, success
depends heavily on the assumption that the ground truth function is symmetric over the …

Topological obstructions and how to avoid them

B Esmaeili, R Walters, H Zimmermann… - Advances in …, 2024 - proceedings.neurips.cc
Incorporating geometric inductive biases into models can aid interpretability and
generalization, but encoding to a specific geometric structure can be challenging due to the …

Back to the manifold: Recovering from out-of-distribution states

A Reichlin, GL Marchetti, H Yin… - 2022 IEEE/RSJ …, 2022 - ieeexplore.ieee.org
Learning from previously collected datasets of expert data offers the promise of acquiring
robotic policies without unsafe and costly online explorations. However, a major challenge is …

Latent Space Symmetry Discovery

J Yang, N Dehmamy, R Walters, R Yu - arXiv preprint arXiv:2310.00105, 2023 - arxiv.org
Equivariant neural networks require explicit knowledge of the symmetry group. Automatic
symmetry discovery methods aim to relax this constraint and learn invariance and …

Soft Contrastive Cross-Modal Retrieval

J Song, Y Hu, L Zhu, C Zhang, J Zhang, S Zhang - Applied Sciences, 2024 - mdpi.com
Cross-modal retrieval plays a key role in the Natural Language Processing area, which aims
to retrieve one modality to another efficiently. Despite the notable achievements of existing …

Learning Geometric Representations of Objects via Interaction

A Reichlin, GL Marchetti, H Yin, A Varava… - … European Conference on …, 2023 - Springer
We address the problem of learning representations from observations of a scene involving
an agent and an external object the agent interacts with. To this end, we propose a …