# Factors of Transferability for a Generic ConvNet Representation

arXiv: https://arxiv.org/abs/1406.5774 · HTML: https://mlsanity.com/paper/1406.5774/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2014.

## Built on by (most cited first, 14 of 14)

- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [MultiRes-NetVLAD: Augmenting Place Recognition Training with Low-Resolution Imagery](https://mlsanity.com/paper/2202.09146/) (2022)
- [RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations](https://mlsanity.com/paper/2412.01826/) (2024)
- [Semantic Pose Verification for Outdoor Visual Localization with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2203.16945/) (2022)
- [Evaluating Contrastive Models for Instance-based Image Retrieval](https://mlsanity.com/paper/2104.14939/) (2021)
- [Construct Informative Triplet with Two-stage Hard-sample Generation](https://mlsanity.com/paper/2112.02259/) (2021)
- [Unifying Remote Sensing Image Retrieval and Classification with Robust Fine-tuning](https://mlsanity.com/paper/2102.13392/) (2021)
- [Cats, not CAT scans: a study of dataset similarity in transfer learning for 2D medical image classification](https://mlsanity.com/paper/2107.05940/) (2021)
- [Shapley variable importance cloud for machine learning models](https://mlsanity.com/paper/2212.08370/) (2022)
- [Understanding the Distributions of Aggregation Layers in Deep Neural Networks](https://mlsanity.com/paper/2107.04458/) (2021)
- [Adaptive Transfer Learning: a simple but effective transfer learning](https://mlsanity.com/paper/2111.10937/) (2021)
- [Learning Deep Representations via Contrastive Learning for Instance Retrieval](https://mlsanity.com/paper/2209.13832/) (2022)
- [Supervised Fine-tuning Evaluation for Long-term Visual Place Recognition](https://mlsanity.com/paper/2211.07696/) (2022)
- [Student Activity Recognition in Classroom Environments using Transfer Learning](https://mlsanity.com/paper/2312.00348/) (2023)

## Abstract (arXiv)

Evidence is mounting that Convolutional Networks (ConvNets) are the most effective representation learning method for visual recognition tasks. In the common scenario, a ConvNet is trained on a large labeled dataset (source) and the feed-forward units activation of the trained network, at a certain layer of the network, is used as a generic representation of an input image for a task with relatively smaller training set (target). Recent studies have shown this form of representation transfer to be suitable for a wide range of target visual recognition tasks. This paper introduces and investigates several factors affecting the transferability of such representations. It includes parameters for training of the source ConvNet such as its architecture, distribution of the training data, etc. and also the parameters of feature extraction such as layer of the trained ConvNet, dimensionality reduction, etc. Then, by optimizing these factors, we show that significant improvements can be achieved on various (17) visual recognition tasks. We further show that these visual recognition tasks can be categorically ordered based on their distance from the source task such that a correlation between the performance of tasks and their distance from the source task w.r.t. the proposed factors is observed.