Geometric Anchor Correspondence Mining with Uncertainty Modeling for Universal Domain Adaptation

Universal domain adaptation (UniDA) aims to transfer the knowledge learned from a label-rich source domain to a label-scarce target domain without any constraints on the label space. However, domain shift and category shift make UniDA extremely challenging, which mainly lies in how to recognize both...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 16113 - 16122
Hlavní autoři: Chen, Liang, Lou, Yihang, He, Jianzhong, Bai, Tao, Deng, Minghua
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2022
Témata:
Adaptation models
Computational modeling
Computer vision
Logic gates
Manifolds
Representation learning
Representation learning; Machine learning; Self-& semi-& meta- Transfer/low-shot/long-tail learning
Uncertainty
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Universal domain adaptation (UniDA) aims to transfer the knowledge learned from a label-rich source domain to a label-scarce target domain without any constraints on the label space. However, domain shift and category shift make UniDA extremely challenging, which mainly lies in how to recognize both shared "known" samples and private "unknown" samples. Previous works rarely explore the intrinsic geometrical relationship between the two domains, and they manually set a threshold for the overconfident closed-world classifier to reject "unknown" samples. Therefore, in this paper, we propose a Geometric anchor-guided Adversarial and conTrastive learning framework with uncErtainty modeling called GATE to alleviate these issues. Specifically, we first develop a random walk-based anchor mining strategy together with a high-order attention mechanism to build correspondence across domains. Then a global joint local domain alignment paradigm is designed, i.e., geometric adversarial learning for global distribution calibration and subgraph-level contrastive learning for local region aggregation. Toward accurate target private samples detection, GATE introduces a universal incremental classifier by modeling the energy uncertainty. We further efficiently generate novel categories by manifold mixup, and minimize the open-set entropy to learn the "unknown" threshold adaptively. Extensive experiments on three benchmarks demonstrate that GATE significantly out-performs previous state-of-the-art UniDA methods.
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.01566