AH-OCDA: Amplitude-based Curriculum Learning and Hopfield Segmentation Model for Open Compound Domain Adaptation

2024-12-03 · Jaehyun Choi, Junwon Ko, Dong-Jae Lee, Junmo Kim

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.

📄 PDF Abstract BibTeX arXiv:2412.02280

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation Segmentation Semantic Segmentation

Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation

2022-02-09 · Jogendra Nath Kundu, Akshay Kulkarni, Suvaansh Bhambri, Varun Jampani 외

Open compound domain adaptation (OCDA) has emerged as a practical adaptation setting which considers a single labeled source domain against a compound of multi-modal unlabeled target data in order to generalize better on…

Disentanglement Domain Adaptation Scene Segmentation Semantic Segmentation

Open Compound Domain Adaptation

2019-09-08 · CVPR 2020 6 · Ziwei Liu, Zhongqi Miao, Xingang Pan, Xiaohang Zhan 외

A typical domain adaptation approach is to adapt models trained on the annotated data in a source domain (e.g., sunny weather) for achieving high performance on the test data in a target domain (e.g., rainy weather). Whe…

Domain Adaptation Facial Expression Recognition Facial Expression Recognition (FER)Reinforcement Learning+1

SCMix: Stochastic Compound Mixing for Open Compound Domain Adaptation in Semantic Segmentation

2024-05-23 · Kai Yao, Zhaorui Tan, Zixian Su, Xi Yang 외

Open compound domain adaptation (OCDA) aims to transfer knowledge from a labeled source domain to a mix of unlabeled homogeneous compound target domains while generalizing to open unseen domains. Existing OCDA methods so…

Domain Adaptation Semantic Segmentation

Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation

2020-12-15 · CVPR 2021 1 · Rui Gong, Yuhua Chen, Danda Pani Paudel, Yawei Li 외

Open compound domain adaptation (OCDA) is a domain adaptation setting, where target domain is modeled as a compound of multiple unknown homogeneous domains, which brings the advantage of improved generalization to unseen…

Domain Adaptation Meta-Learning Semantic Segmentation Transfer Learning

ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation

2022-07-19 · Fei Pan, Sungsu Hur, Seokju Lee, Junsik Kim 외

Open compound domain adaptation (OCDA) considers the target domain as the compound of multiple unknown homogeneous subdomains. The goal of OCDA is to minimize the domain gap between the labeled source domain and the unla…