# AdaFilter: Adaptive Filter Fine-tuning for Deep Transfer Learning

arXiv: https://arxiv.org/abs/1911.09659 · HTML: https://mlsanity.com/paper/1911.09659/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2019.

## Built on by (most cited first, 12 of 12)

- [Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.08566/) (2023)
- [INTERN: A New Learning Paradigm Towards General Vision](https://mlsanity.com/paper/2111.08687/) (2021)
- [Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation](https://mlsanity.com/paper/2309.13192/) (2023)
- [ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection](https://mlsanity.com/paper/2312.14227/) (2023)
- [Advancing 3D Point Cloud Understanding through Deep Transfer Learning: A Comprehensive Survey](https://mlsanity.com/paper/2407.17877/) (2024)
- [Agile Multi-Source-Free Domain Adaptation](https://mlsanity.com/paper/2403.05062/) (2024)
- [Robust and Explainable Fine-Grained Visual Classification with Transfer Learning: A Dual-Carriageway Framework](https://mlsanity.com/paper/2405.05853/) (2024)
- [AC-Norm: Effective Tuning for Medical Image Analysis via Affine Collaborative Normalization](https://mlsanity.com/paper/2307.15282/) (2023)
- [On the low-shot transferability of [V]-Mamba](https://mlsanity.com/paper/2403.10696/) (2024)
- [KITE: A Kernel-based Improved Transferability Estimation Method](https://mlsanity.com/paper/2405.01603/) (2024)
- [Adaptive Transfer Learning: a simple but effective transfer learning](https://mlsanity.com/paper/2111.10937/) (2021)
- [One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data](https://mlsanity.com/paper/2111.12386/) (2021)

## Abstract (arXiv)

There is an increasing number of pre-trained deep neural network models. However, it is still unclear how to effectively use these models for a new task. Transfer learning, which aims to transfer knowledge from source tasks to a target task, is an effective solution to this problem. Fine-tuning is a popular transfer learning technique for deep neural networks where a few rounds of training are applied to the parameters of a pre-trained model to adapt them to a new task. Despite its popularity, in this paper, we show that fine-tuning suffers from several drawbacks. We propose an adaptive fine-tuning approach, called AdaFilter, which selects only a part of the convolutional filters in the pre-trained model to optimize on a per-example basis. We use a recurrent gated network to selectively fine-tune convolutional filters based on the activations of the previous layer. We experiment with 7 public image classification datasets and the results show that AdaFilter can reduce the average classification error of the standard fine-tuning by 2.54%.