Research map / Architectures and efficiency / Pruning and efficient tuning
TransTailor: Pruning the Pre-trained Model for Improved Transfer Learning
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 target-aware filter importance for pruning instead of source-task pruning | ResNet-101 transfer learning · Stanford Dogs | Top-1 accuracy: 89.0% -> 91.0% | Helped |
| Use target-aware filter importance for pruning instead of source-task pruning | ResNet-101 transfer learning · CUB-200 | Top-1 accuracy: 80.7% -> 80.7% | No clear effect |
| Prune the structure using TransTailor rather than fine-tuning all parameters | VGG-16 transfer learning · Stanford Dogs | Top-1 accuracy: 82.6% -> 84.2% | Helped |
| Prune the structure using TransTailor rather than fine-tuning all parameters | VGG-16 transfer learning · MIT Indoor-67 | Top-1 accuracy: 76.3% -> 76.5% | Helped |
| Use TransTailor instead of DELTA | ResNet-101 transfer learning · Caltech256-30 | Top-1 accuracy: 85.7% -> 85.3% | Hurt |
| Use TransTailor instead of DELTA | ResNet-101 transfer learning · CUB-200 | Top-1 accuracy: 78.9% -> 80.7% | Helped |
| Prune 50% FLOPs with target-aware pruning | ResNet-101 transfer learning · Stanford Dogs | Top-1 accuracy relative to other pruning baselines: 8.1% | Helped |
| Use target-aware pruning rather than no structural pruning | ResNet-101 transfer learning · CUB-200 | Top-1 accuracy | Helped |
Closest papers by meaning
- Transferring Knowledge From Large Foundation Models to Small Downstream Models (ICML 2024 · similarity 0.86)
- Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing (NeurIPS 2026 · similarity 0.85)
- Understanding the Transferability of Representations via Task-Relatedness (NeurIPS 2024 · similarity 0.84)
- Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How (ICLR 2024 · similarity 0.84)
- A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning (NeurIPS 2025 · similarity 0.84)
- Feature Reuse and Scaling: Understanding Transfer Learning with Protein Language Models (ICML 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.