# Adaptive Deep Learning through Visual Domain Localization

arXiv: https://arxiv.org/abs/1802.08833 · HTML: https://mlsanity.com/paper/1802.08833/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Feb 2018.

## Built on by (most cited first, 6 of 6)

- [Inferring Latent Domains for Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/2103.13873/) (2021)
- [Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation](https://mlsanity.com/paper/2103.14496/) (2021)
- [A separability-based approach to quantifying generalization: which layer is best?](https://mlsanity.com/paper/2405.01524/) (2024)
- [On the Challenges of Open World Recognitionunder Shifting Visual Domains](https://mlsanity.com/paper/2107.04461/) (2021)
- [Exploring Data Aggregation and Transformations to Generalize across Visual Domains](https://mlsanity.com/paper/2108.09208/) (2021)
- [Contrastive Learning for Cross-Domain Open World Recognition](https://mlsanity.com/paper/2203.09257/) (2022)

## Abstract (arXiv)

A commercial robot, trained by its manufacturer to recognize a predefined number and type of objects, might be used in many settings, that will in general differ in their illumination conditions, background, type and degree of clutter, and so on. Recent computer vision works tackle this generalization issue through domain adaptation methods, assuming as source the visual domain where the system is trained and as target the domain of deployment. All approaches assume to have access to images from all classes of the target during training, an unrealistic condition in robotics applications. We address this issue proposing an algorithm that takes into account the specific needs of robot vision. Our intuition is that the nature of the domain shift experienced mostly in robotics is local. We exploit this through the learning of maps that spatially ground the domain and quantify the degree of shift, embedded into an end-to-end deep domain adaptation architecture. By explicitly localizing the roots of the domain shift we significantly reduce the number of parameters of the architecture to tune, we gain the flexibility necessary to deal with subset of categories in the target domain at training time, and we provide a clear feedback on the rationale behind any classification decision, which can be exploited in human-robot interactions. Experiments on two different settings of the iCub World database confirm the suitability of our method for robot vision.