AH-OCDA: Amplitude-based Curriculum Learning and Hopfield Segmentation Model for Open Compound Domain Adaptation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912142009040896 |
|---|---|
| author | Choi, Jaehyun Ko, Junwon Lee, Dong-Jae Kim, Junmo |
| author_facet | Choi, Jaehyun Ko, Junwon Lee, Dong-Jae Kim, Junmo |
| contents | Open compound domain adaptation (OCDA) is a practical domain adaptation problem that consists of a source domain, target compound domain, and unseen open domain. In this problem, the absence of domain labels and pixel-level segmentation labels for both compound and open domains poses challenges to the direct application of existing domain adaptation and generalization methods. To address this issue, we propose Amplitude-based curriculum learning and a Hopfield segmentation model for Open Compound Domain Adaptation (AH-OCDA). Our method comprises two complementary components: 1) amplitude-based curriculum learning and 2) Hopfield segmentation model. Without prior knowledge of target domains within the compound domains, amplitude-based curriculum learning gradually induces the semantic segmentation model to adapt from the near-source compound domain to the far-source compound domain by ranking unlabeled compound domain images through Fast Fourier Transform (FFT). Additionally, the Hopfield segmentation model maps segmentation feature distributions from arbitrary domains to the feature distributions of the source domain. AH-OCDA achieves state-of-the-art performance on two OCDA benchmarks and extended open domains, demonstrating its adaptability to continuously changing compound domains and unseen open domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_02280 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AH-OCDA: Amplitude-based Curriculum Learning and Hopfield Segmentation Model for Open Compound Domain Adaptation Choi, Jaehyun Ko, Junwon Lee, Dong-Jae Kim, Junmo Artificial Intelligence Computer Vision and Pattern Recognition Open compound domain adaptation (OCDA) is a practical domain adaptation problem that consists of a source domain, target compound domain, and unseen open domain. In this problem, the absence of domain labels and pixel-level segmentation labels for both compound and open domains poses challenges to the direct application of existing domain adaptation and generalization methods. To address this issue, we propose Amplitude-based curriculum learning and a Hopfield segmentation model for Open Compound Domain Adaptation (AH-OCDA). Our method comprises two complementary components: 1) amplitude-based curriculum learning and 2) Hopfield segmentation model. Without prior knowledge of target domains within the compound domains, amplitude-based curriculum learning gradually induces the semantic segmentation model to adapt from the near-source compound domain to the far-source compound domain by ranking unlabeled compound domain images through Fast Fourier Transform (FFT). Additionally, the Hopfield segmentation model maps segmentation feature distributions from arbitrary domains to the feature distributions of the source domain. AH-OCDA achieves state-of-the-art performance on two OCDA benchmarks and extended open domains, demonstrating its adaptability to continuously changing compound domains and unseen open domains. |
| title | AH-OCDA: Amplitude-based Curriculum Learning and Hopfield Segmentation Model for Open Compound Domain Adaptation |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.02280 |