Search
Results
-
mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasets
(2021)2021 IEEE/CVF International Conference on Computer Vision (ICCV)One challenge of object recognition is to generalize to new domains, to more classes and/or to new modalities. This necessitates methods to combine and reuse existing datasets that may belong to different domains, have partial annotations, and/or have different data modalities. This paper formulates this as a multi-source domain adaptation and label unification problem, and proposes a novel method for it. Our method consists of a ...Conference Paper -
Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation
(2021)2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)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 domains. In this work, we propose a principled meta-learning based approach to OCDA for semantic segmentation, MOCDA, by modeling the unlabeled target domain continuously. Our approach consists of four key steps. First, ...Conference Paper -
TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation
(2022)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2022Traditional domain adaptive semantic segmentation addresses the task of adapting a model to a novel target domain under limited or no additional supervision. While tackling the input domain gap, the standard domain adaptation settings assume no domain change in the output space. In semantic prediction tasks, different datasets are often labeled according to different semantic taxonomies. In many real-world settings, the target domain task ...Conference Paper -
Analogical Image Translation for Fog Generation
(2021)Proceedings of the AAAI Conference on Artificial IntelligenceImage-to-image translation is to map images from a given style to another given style. While exceptionally successful, current methods assume the availability of training images in both source and target domains, which does not always hold in practice. Inspired by humans' reasoning capability of analogy, we propose analogical image translation (AIT) that exploit the concept of gist, for the first time. Given images of two styles in the ...Conference Paper -
Continuous Pseudo-Label Rectified Domain Adaptive Semantic Segmentation with Implicit Neural Representations
(2023)2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Unsupervised domain adaptation (UDA) for semantic segmentation aims at improving the model performance on the unlabeled target domain by leveraging a labeled source domain. Existing approaches have achieved impressive progress by utilizing pseudo-labels on the unlabeled target-domain images. Yet the low-quality pseudo-labels, arising from the domain discrepancy, inevitably hinder the adaptation. This calls for effective and accurate ...Conference Paper