Research map / Architectures and efficiency / Pruning and efficient tuning
Deep Model Reassembly
Xingyi Yang, Zhou Daquan, Songhua Liu, Jingwen Ye, Xinchao Wang
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 |
|---|---|---|---|
| Reassemble a homogeneous model zoo with DeRy instead of Zoo Tuning | Homogeneous model zoo · CIFAR-100 | accuracy: 83.39 -> 84.05 | Improved |
| Reassemble a homogeneous model zoo with DeRy instead of Zoo Tuning | Homogeneous model zoo · AirCraft | accuracy: 85.51 -> 88.86 | Improved |
| Reassemble a homogeneous model zoo with DeRy instead of Zoo Tuning | Homogeneous model zoo · Cars | accuracy: 89.73 -> 93.86 | Improved |
| Increase the partition number from K=4 to K=5 (ablation) | DeRy · ImageNet | Top1 Acc: 79.63 -> 79.68 | No clear effect |
| Increase the partition number from K=4 to K=6 (ablation) | DeRy · ImageNet | Top1 Acc: 79.63 -> 79.83 | No clear effect |
| Use random weight initialization instead of DeRy's pre-trained weights (ablation) | DeRy · Nine transfer learning datasets | test accuracy | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Zoo Tuning — Zoo-Tuning: Adaptive Transfer from A Zoo of Models (ICML 2021) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks (NeurIPS 2024 · similarity 0.88)
- ModHiFi: Identifying High Fidelity predictive components for Model Modification (NeurIPS 2025 · similarity 0.86)
- Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model (ICLR 2024 · similarity 0.85)
- Rethinking Layer-wise Model Merging through Chain of Merges (NeurIPS 2026 · similarity 0.85)
- ZipIt! Merging Models from Different Tasks without Training (ICLR 2024 · similarity 0.85)
- Merging on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging (NeurIPS 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.
