# Simultaneous Semantic Alignment Network for Heterogeneous Domain Adaptation

arXiv: https://arxiv.org/abs/2008.01677 · HTML: https://mlsanity.com/paper/2008.01677/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2020.

## Built on by (most cited first, 21 of 21)

- [HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning](https://mlsanity.com/paper/2109.15163/) (2021)
- [Semi-Supervised and Unsupervised Deep Visual Learning: A Survey](https://mlsanity.com/paper/2208.11296/) (2022)
- [Cross-Modal Fine-Tuning: Align then Refine](https://mlsanity.com/paper/2302.05738/) (2023)
- [ZiGAN: Fine-grained Chinese Calligraphy Font Generation via a Few-shot Style Transfer Approach](https://mlsanity.com/paper/2108.03596/) (2021)
- [Rethinking Domain Generalization: Discriminability and Generalizability](https://mlsanity.com/paper/2309.16483/) (2023)
- [I2V-GAN: Unpaired Infrared-to-Visible Video Translation](https://mlsanity.com/paper/2108.00913/) (2021)
- [Cross-user activity recognition via temporal relation optimal transport](https://mlsanity.com/paper/2403.15423/) (2024)
- [Joint Semantic Transfer Network for IoT Intrusion Detection](https://mlsanity.com/paper/2210.15911/) (2022)
- [Rethinking Guidance Information to Utilize Unlabeled Samples:A Label Encoding Perspective](https://mlsanity.com/paper/2406.02862/) (2024)
- [Heterogeneous Domain Adaptation for IoT Intrusion Detection: A Geometric Graph Alignment Approach](https://mlsanity.com/paper/2301.09801/) (2023)
- [Deep Generative Domain Adaptation with Temporal Relation Knowledge for Cross-User Activity Recognition](https://mlsanity.com/paper/2403.14682/) (2024)
- [Deep Generative Domain Adaptation with Temporal Attention for Cross-User Activity Recognition](https://mlsanity.com/paper/2403.17958/) (2024)
- [GLA-DA: Global-Local Alignment Domain Adaptation for Multivariate Time Series](https://mlsanity.com/paper/2410.06671/) (2024)
- [Keypoint-Guided Optimal Transport: Models, Algorithms, and Applications](https://mlsanity.com/paper/2303.13102/) (2023)
- [Adaptive Bi-Recommendation and Self-Improving Network for Heterogeneous Domain Adaptation-Assisted IoT Intrusion Detection](https://mlsanity.com/paper/2303.14317/) (2023)
- [Open Set Dandelion Network for IoT Intrusion Detection](https://mlsanity.com/paper/2311.11249/) (2023)
- [Unifying Visual and Semantic Feature Spaces with Diffusion Models for Enhanced Cross-Modal Alignment](https://mlsanity.com/paper/2407.18854/) (2024)
- [Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction Between Feature Alignment and Target Fitting](https://mlsanity.com/paper/2601.18231/) (2026)
- [Cross-user activity recognition using deep domain adaptation with temporal relation information](https://mlsanity.com/paper/2403.15424/) (2024)
- [Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm](https://mlsanity.com/paper/2412.13036/) (2024)
- [Multi-Level Heterogeneous Knowledge Transfer Network on Forward Scattering Center Model for Limited Samples SAR ATR](https://mlsanity.com/paper/2509.23596/) (2025)

## Abstract (arXiv)

Heterogeneous domain adaptation (HDA) transfers knowledge across source and target domains that present heterogeneities e.g., distinct domain distributions and difference in feature type or dimension. Most previous HDA methods tackle this problem through learning a domain-invariant feature subspace to reduce the discrepancy between domains. However, the intrinsic semantic properties contained in data are under-explored in such alignment strategy, which is also indispensable to achieve promising adaptability. In this paper, we propose a Simultaneous Semantic Alignment Network (SSAN) to simultaneously exploit correlations among categories and align the centroids for each category across domains. In particular, we propose an implicit semantic correlation loss to transfer the correlation knowledge of source categorical prediction distributions to target domain. Meanwhile, by leveraging target pseudo-labels, a robust triplet-centroid alignment mechanism is explicitly applied to align feature representations for each category. Notably, a pseudo-label refinement procedure with geometric similarity involved is introduced to enhance the target pseudo-label assignment accuracy. Comprehensive experiments on various HDA tasks across text-to-image, image-to-image and text-to-text successfully validate the superiority of our SSAN against state-of-the-art HDA methods. The code is publicly available at https://github.com/BIT-DA/SSAN.