Research map / Label-efficient and robust learning / Domain adaptation and generalization
MemFlow: A Lightweight Forward Memorizing Framework for Quick Domain Adaptive Feature Mapping
Jianming Lv, Chengjun Wang, Depin Liang, Qianli Ma, Wei Chen, Xueqi Cheng
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 Confidence-based Update (to the variant with no components) (ablation) | MemFlow · Office-31 | accuracy: 73.46 -> 84.97 | Improved |
| add Gaussian Blur fuzzy memory to the variant with no components (ablation) | MemFlow · Office-Home | accuracy: 42.54 -> 65.04 | Improved |
| add Gaussian Blur fuzzy memory to the variant with no components (ablation) | MemFlow · VisDA-C | accuracy: 35.94 -> 70.96 | Improved |
| add Gaussian Blur fuzzy memory to the variant with no components (ablation) | MemFlow · Digits | accuracy: 60.68 -> 89.00 | Improved |
| add Gaussian Blur fuzzy memory to the variant with no components (ablation) | MemFlow · Office-31 | accuracy: 73.46 -> 84.59 | Improved |
| add Confidence-based Update to the GB-only variant (ablation) | MemFlow · VisDA-C | accuracy: 70.96 -> 71.14 | Improved |
| add Confidence-based Update to the GB-only variant (ablation) | MemFlow · Office-Home | accuracy: 65.04 -> 65.84 | Improved |
| add Spiking Mechanism to the CU+GB variant (ablation) | MemFlow · VisDA-C | accuracy: 71.14 -> 72.08 | Improved |
| add Spiking Mechanism to the CU+GB variant (ablation) | MemFlow · Office-31 | accuracy: 85.52 -> 86.08 | Improved |
| add Spiking Mechanism to the CU+GB variant (ablation) | MemFlow · Digits | accuracy: 89.07 -> 89.14 | Improved |
| plug MemFlow into SHOT | SHOT · Office-Home | accuracy: 71.0 -> 72.3 | Improved |
| plug MemFlow into AaD | AaD · Office-Home | accuracy: 72.2 -> 72.8 | Improved |
Closest papers by meaning
- MemDLM: Memory-Enhanced DLM Training (NeurIPS 2026 · similarity 0.84)
- MemFlow: Optical Flow Estimation and Prediction with Memory (CVPR 2024 · similarity 0.83)
- ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think (ICML 2025 · similarity 0.83)
- Rapid Learning without Catastrophic Forgetting in the Morris Water Maze (ICML 2024 · similarity 0.83)
- An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning (NeurIPS 2024 · similarity 0.82)
- Time- Memory- and Parameter-Efficient Visual Adaptation (CVPR 2024 · similarity 0.82)
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.
