# Disjoint Label Space Transfer Learning with Common Factorised Space

arXiv: https://arxiv.org/abs/1812.02605 · HTML: https://mlsanity.com/paper/1812.02605/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2018.

## Built on by (most cited first, 13 of 13)

- [Group-aware Label Transfer for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2103.12366/) (2021)
- [Towards Discriminative Representation Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2108.03439/) (2021)
- [Cross-domain few-shot learning with unlabelled data](https://mlsanity.com/paper/2101.07899/) (2021)
- [Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-Identification](https://mlsanity.com/paper/2112.14025/) (2021)
- [Dual-Stream Reciprocal Disentanglement Learning for Domain Adaptation Person Re-Identification](https://mlsanity.com/paper/2106.13929/) (2021)
- [Mind the Gap Between Synthetic and Real: Utilizing Transfer Learning to Probe the Boundaries of Stable Diffusion Generated Data](https://mlsanity.com/paper/2405.03243/) (2024)
- [Transfer Learning with Pre-trained Conditional Generative Models](https://mlsanity.com/paper/2204.12833/) (2022)
- [Machine learning with limited data](https://mlsanity.com/paper/2101.11461/) (2021)
- [Improving Unsupervised Domain Adaptive Re-Identification via Source-Guided Selection of Pseudo-Labeling Hyperparameters](https://mlsanity.com/paper/2110.07897/) (2021)
- [A formal approach to good practices in Pseudo-Labeling for Unsupervised Domain Adaptive Re-Identification](https://mlsanity.com/paper/2112.12887/) (2021)
- [Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning](https://mlsanity.com/paper/2301.12439/) (2023)
- [Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2103.13917/) (2021)
- [Unsupervised Domain Adaptive Person Re-Identification via Human Learning Imitation](https://mlsanity.com/paper/2111.14014/) (2021)

## Abstract (arXiv)

In this paper, a unified approach is presented to transfer learning that addresses several source and target domain label-space and annotation assumptions with a single model. It is particularly effective in handling a challenging case, where source and target label-spaces are disjoint, and outperforms alternatives in both unsupervised and semi-supervised settings. The key ingredient is a common representation termed Common Factorised Space. It is shared between source and target domains, and trained with an unsupervised factorisation loss and a graph-based loss. With a wide range of experiments, we demonstrate the flexibility, relevance and efficacy of our method, both in the challenging cases with disjoint label spaces, and in the more conventional cases such as unsupervised domain adaptation, where the source and target domains share the same label-sets.