# Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization

arXiv: https://arxiv.org/abs/1904.08631 · HTML: https://mlsanity.com/paper/1904.08631/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2019.

## Built on by (most cited first, 10 of 10)

- [Upcycling Models under Domain and Category Shift](https://mlsanity.com/paper/2303.07110/) (2023)
- [Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain Adaptation](https://mlsanity.com/paper/2107.06154/) (2021)
- [Towards Novel Target Discovery Through Open-Set Domain Adaptation](https://mlsanity.com/paper/2105.02432/) (2021)
- [Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptation](https://mlsanity.com/paper/2103.11661/) (2021)
- [Orthogonal Temporal Interpolation for Zero-Shot Video Recognition](https://mlsanity.com/paper/2308.06897/) (2023)
- [GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning](https://mlsanity.com/paper/2403.14410/) (2024)
- [Combat Data Shift in Few-shot Learning with Knowledge Graph](https://mlsanity.com/paper/2101.11354/) (2021)
- [Confusing Pair Correction Based on Category Prototype for Domain Adaptation under Noisy Environments](https://mlsanity.com/paper/2403.12883/) (2024)
- [Open Set Domain Recognition via Attention-Based GCN and Semantic Matching Optimization](https://mlsanity.com/paper/2105.04967/) (2021)
- [Semantic Relation-Enhanced CLIP Adapter for Domain Adaptive Zero-Shot Learning](https://mlsanity.com/paper/2510.21808/) (2025)

## Abstract (arXiv)

We address the unsupervised open domain recognition (UODR) problem, where categories in labeled source domain S is only a subset of those in unlabeled target domain T. The task is to correctly classify all samples in T including known and unknown categories. UODR is challenging due to the domain discrepancy, which becomes even harder to bridge when a large number of unknown categories exist in T. Moreover, the classification rules propagated by graph CNN (GCN) may be distracted by unknown categories and lack generalization capability. To measure the domain discrepancy for asymmetric label space between S and T, we propose Semantic-Guided Matching Discrepancy (SGMD), which first employs instance matching between S and T, and then the discrepancy is measured by a weighted feature distance between matched instances. We further design a limited balance constraint to achieve a more balanced classification output on known and unknown categories. We develop Unsupervised Open Domain Transfer Network (UODTN), which learns both the backbone classification network and GCN jointly by reducing the SGMD, enforcing the limited balance constraint and minimizing the classification loss on S. UODTN better preserves the semantic structure and enforces the consistency between the learned domain invariant visual features and the semantic embeddings. Experimental results show superiority of our method on recognizing images of both known and unknown categories.