equivariance
Neural Functional Transformers Allan Zhou
However, developing models that can process weight-space objects is challenging due to their high dimensional nature.
Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation
A truly generalizable approach to rigid segmentation and motion estimation is fundamental to 3D understanding of articulated objects and moving scenes.
- Asia > Middle East > Israel (0.04)
- Europe > United Kingdom > England > Tyne and Wear > Newcastle (0.04)
- Europe > United Kingdom > England > Oxfordshire > Oxford (0.04)
- (2 more...)
Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance
Any explanation that faithfully explains this type of model needs to be in agreement with this invariance property.
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- North America > United States > Oregon > Multnomah County > Portland (0.04)
- North America > United States > Florida > Broward County > Fort Lauderdale (0.04)
- (2 more...)
A new perspective on building efficient and expressive 3D equivariant graph neural networks
Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects.
- South America > Chile > Santiago Metropolitan Region > Santiago Province > Santiago (0.04)
- North America > United States > Texas > Brazos County > College Station (0.04)
- Asia > China > Guangxi Province > Nanning (0.04)
- Overview (0.92)
- Research Report (0.67)
- Energy (0.46)
- Health & Medicine > Pharmaceuticals & Biotechnology (0.46)
- South America > Chile > Santiago Metropolitan Region > Santiago Province > Santiago (0.04)
- North America > United States > Texas > Brazos County > College Station (0.04)
- Asia > China > Guangxi Province > Nanning (0.04)
- Overview (0.92)
- Research Report (0.67)
- Energy (0.46)
- Health & Medicine > Pharmaceuticals & Biotechnology (0.46)
Equivariant Neural Operator Learning with Graphon Convolution
It is common that these data themselves have inherently complicated 3D geometric structures.
- Oceania > Australia > New South Wales > Sydney (0.04)
- North America > United States > Illinois > Champaign County > Urbana (0.04)
- Europe > Germany > Bavaria > Upper Bavaria > Munich (0.04)
- (9 more...)
- Materials > Chemicals > Commodity Chemicals > Petrochemicals (0.68)
- Health & Medicine (0.68)
Equivariant Neural Operator Learning with Graphon Convolution
It is common that these data themselves have inherently complicated 3D geometric structures.
- Oceania > Australia > New South Wales > Sydney (0.04)
- North America > United States > Illinois > Champaign County > Urbana (0.04)
- Europe > Germany > Bavaria > Upper Bavaria > Munich (0.04)
- (9 more...)
- Materials > Chemicals > Commodity Chemicals > Petrochemicals (0.68)
- Health & Medicine (0.68)
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.14)
- South America > Chile > Santiago Metropolitan Region > Santiago Province > Santiago (0.04)
- Oceania > Australia > New South Wales > Sydney (0.04)
- (6 more...)
Equivariant Adaptation of Large Pretrained Models Arnab Kumar Mondal
We show here that this approach can effectively be used to make a large pretrained network equivariant.
- Europe > Switzerland > Zürich > Zürich (0.14)
- North America > Canada > Quebec > Montreal (0.04)
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.04)
- Europe > Spain > Andalusia > Granada Province > Granada (0.04)