Research map / Architectures and efficiency / CNN design
Invariance and Stability of Deep Convolutional Representations
Alberto Bietti, Julien Mairal
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add a kernel mapping that is homogeneous with norm preservation and non-expansiveness (assumptions A1-2) to the multilayer convolutional kernel representation | multilayer convolutional kernel representation · theoretical analysis (continuous signals under diffeomorphisms) | stability bound ||Phi(L_tau x) - Phi(x)|| <= (C1(1+n)||grad tau||_inf + (C2/sigm | Improved |
Closest papers by meaning
- Group Invariance, Stability to Deformations, and Complexity of Deep Convolutional Representations (JMLR 2019 · similarity 0.94)
- Relative stability toward diffeomorphisms indicates performance in deep nets (NeurIPS 2021 · similarity 0.87)
- Exploiting Invariance in Training Deep Neural Networks (AAAI 2022 · similarity 0.86)
- On Making $SE(2)$-Invariant Networks Optimal (NeurIPS 2026 · similarity 0.86)
- Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity (ICLR 2025 · similarity 0.85)
- Unitary Convolutions for Learning on Graphs and Groups (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
