Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.
Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Hallucinations in diffusion models are driven by local intrinsic dimension instabilities on the manifold, which Intrinsic Quenching corrects by deflating it.
TripoSG generates high-fidelity 3D meshes from input images via a large-scale rectified flow transformer and hybrid-trained 3D VAE on a custom 2-million-sample dataset, claiming state-of-the-art fidelity and generalization.
A perturbation-based metric for XAI quality that formalizes sufficiency and necessity, paired with an adapter trained via differentiable supervision to generate causal explanations on black-box models.
citing papers explorer
-
Pointwise Generalization in Deep Neural Networks
Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.
-
Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models
Hallucinations in diffusion models are driven by local intrinsic dimension instabilities on the manifold, which Intrinsic Quenching corrects by deflating it.
-
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
TripoSG generates high-fidelity 3D meshes from input images via a large-scale rectified flow transformer and hybrid-trained 3D VAE on a custom 2-million-sample dataset, claiming state-of-the-art fidelity and generalization.
-
Learning Quantifiable Visual Explanations Without Ground-Truth
A perturbation-based metric for XAI quality that formalizes sufficiency and necessity, paired with an adapter trained via differentiable supervision to generate causal explanations on black-box models.
- DIVER:Diving Deeper into Distilled Data via Expressive Semantic Recovery