# One-Shot Adaptation of Supervised Deep Convolutional Models

arXiv: https://arxiv.org/abs/1312.6204 · HTML: https://mlsanity.com/paper/1312.6204/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2013.

## Built on by (most cited first, 9 of 9)

- [A Broad Study of Pre-training for Domain Generalization and Adaptation](https://mlsanity.com/paper/2203.11819/) (2022)
- [Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation](https://mlsanity.com/paper/2203.02135/) (2022)
- [Few-Shot Adaptation of Pre-Trained Networks for Domain Shift](https://mlsanity.com/paper/2205.15234/) (2022)
- [AGI for Agriculture](https://mlsanity.com/paper/2304.06136/) (2023)
- [BatStyler: Advancing Multi-category Style Generation for Source-free Domain Generalization](https://mlsanity.com/paper/2501.01109/) (2025)
- [Evaluation of Deep Neural Network Domain Adaptation Techniques for Image Recognition](https://mlsanity.com/paper/2109.13420/) (2021)
- [1st Place Solution to NeurIPS 2022 Challenge on Visual Domain Adaptation](https://mlsanity.com/paper/2211.14596/) (2022)
- [One shot learning based drivers head movement identification using a millimetre wave radar sensor](https://mlsanity.com/paper/2306.05291/) (2023)
- [SelectNAdapt: Support Set Selection for Few-Shot Domain Adaptation](https://mlsanity.com/paper/2308.04946/) (2023)

## Abstract (arXiv)

Dataset bias remains a significant barrier towards solving real world computer vision tasks. Though deep convolutional networks have proven to be a competitive approach for image classification, a question remains: have these models have solved the dataset bias problem? In general, training or fine-tuning a state-of-the-art deep model on a new domain requires a significant amount of data, which for many applications is simply not available. Transfer of models directly to new domains without adaptation has historically led to poor recognition performance. In this paper, we pose the following question: is a single image dataset, much larger than previously explored for adaptation, comprehensive enough to learn general deep models that may be effectively applied to new image domains? In other words, are deep CNNs trained on large amounts of labeled data as susceptible to dataset bias as previous methods have been shown to be? We show that a generic supervised deep CNN model trained on a large dataset reduces, but does not remove, dataset bias. Furthermore, we propose several methods for adaptation with deep models that are able to operate with little (one example per category) or no labeled domain specific data. Our experiments show that adaptation of deep models on benchmark visual domain adaptation datasets can provide a significant performance boost.