Research map / Detection and segmentation / CNN features
MobileODE: An Extra Lightweight Network
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes MobileODE, an extra lightweight CNN design that replaces depthwise-separable convolution components via a discretization of ordinary differential equations (abstract truncated).
Problem
Reducing the parameter and computation cost of convolutional neural networks beyond depthwise-separable convolution, which splits spatial (depthwise) and channel (pointwise) mixing.
Approach
Lightweight CNN construction via discretization of ordinary differential equations as an alternative to depthwise-separable convolution; the abstract is truncated so the exact mechanism is not stated.
Experimental setup
Builds on: depthwise-separable convolution
Closest papers by meaning
- High Performance Depthwise and Pointwise Convolutions on Mobile Devices (AAAI 2020 · similarity 0.89)
- MnasNet: Platform-Aware Neural Architecture Search for Mobile (CVPR 2019 · similarity 0.89)
- RepViT: Revisiting Mobile CNN From ViT Perspective (CVPR 2024 · similarity 0.87)
- IFORMER: INTEGRATING CONVNET AND TRANSFORMER FOR MOBILE APPLICATION (ICLR 2025 · similarity 0.87)
- LSNet: See Large, Focus Small (CVPR 2025 · similarity 0.86)
- MobileMamba: Lightweight Multi-Receptive Visual Mamba Network (CVPR 2025 · similarity 0.85)
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.