Research map / Architectures and efficiency / CNN design
Dynamic Filter Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use dynamically generated local filters for video prediction | DFN · Moving MNIST | average binary cross-entropy: 367.1 -> 285.2 | Helped |
| Use dynamically generated local filters for video prediction | DFN · Moving MNIST | number of model parameters: 7,585,296 -> 637,361 | Helped |
| Use dynamically generated local filters for video prediction | DFN · Moving MNIST | average binary cross-entropy: 341.2 -> 285.2 | Helped |
Closest papers by meaning
- Decoupled Dynamic Filter Networks (CVPR 2021 · similarity 0.90)
- CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters (CVPR 2022 · similarity 0.89)
- KernelWarehouse: Rethinking the Design of Dynamic Convolution (ICML 2024 · similarity 0.88)
- Temporal Residual Networks for Dynamic Scene Recognition (CVPR 2017 · similarity 0.88)
- Dynamic Convolution: Attention Over Convolution Kernels (CVPR 2020 · similarity 0.88)
- Bi-volution: A Static and Dynamic Coupled Filter (AAAI 2022 · similarity 0.87)
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.