2020/03/31 by Dapeng Hu, Jian Liang, Qibin Hou +2 · 44 citations
Computer Science · Mathematics · Medicine · #Algorithm #Arithmetic #Artificial intelligence #COVID-19 diagnosis using AI #Computer science #Concatenation (mathematics) #Discriminative model #Discriminator #Domain Adaptation and Few-Shot Learning #Machine learning #Mathematics #Multimodal Machine Learning Applications #Pattern recognition (psychology) #Theoretical computer science #cs.CV
paper · pdf · doi:10.1109/tip.2021.3124674
published in IEEE Transactions on Image Processing 30, 9359-9371 (Institute of Electrical and Electronics Engineers) · Published at IEEE transactions on image processing 2021
openalex publication_date 2021/01/01 · arxiv created 2021/12/18 · arxiv updated 2021/12/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Domain adversarial training has become a prevailing and effective paradigm for unsupervised domain adaptation (UDA). To successfully align the multi-modal data structures across domains, the following works exploit discriminative information in the adversarial training process, e.g., using multiple class-wise discriminators and involving conditional information in the input or output of the domain discriminator. However, these methods either require non-trivial model designs or are inefficient for UDA tasks. In this work, we attempt to address this dilemma by devising simple and compact conditional domain adversarial training methods. We first revisit the simple concatenation conditioning strategy where features are concatenated with output predictions as the input of the discriminator. We find the concatenation strategy suffers from the weak conditioning strength. We further demonstrate that enlarging the norm of concatenated predictions can effectively energize the conditional domain alignment. Thus we improve concatenation conditioning by normalizing the output predictions to have the same norm of features, and term the derived method as Normalized OutpUt coNditioner (NOUN). However, conditioning on raw output predictions for domain alignment, NOUN suffers from inaccurate predictions of the target domain. To this end, we propose to condition the cross-domain feature alignment in the prototype space rather than in the output space. Combining the novel prototype-based conditioning with NOUN, we term the enhanced method as PROtotype-based Normalized OutpUt coNditioner (PRONOUN). Experiments on both object recognition and semantic segmentation show that NOUN can effectively align the multi-modal structures across domains and even outperform state-of-the-art domain adversarial training methods. Together with prototype-based conditioning, PRONOUN further improves the adaptation performance over NOUN on multiple object recognition benchmarks for UDA. Code is available at https://github.com/tim-learn/NOUN.