Presentation | 2020-12-17 Hierarchical Contrastive Adaptation for Cross-Domain Object Detection Ziwei Deng, Quan Kong, Naoto Akira, Tomoaki Yoshinaga, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Object detection based on deep learning has been enormously developed in recent years. However, applying detectors trained on a label-rich domain to an unseen domain results in performance drop due to the domain-shift. To deal with this problem, we propose a novel unsupervised domain adaptation framework to adapt the detector from a labeled source domain to an unlabeled target domain. In our proposed method, we utilize the image translation to generate interpolated images of source and target domains to fill in the large domain gap and facilitate a paired adaptation. We propose a hierarchical contrastive adaptation method between the original and interpolated domains to encourage the detectors to learn domain-invariant but discriminative features. To tackle the noises brought by image translation, we further propose a foreground attention reweighting for instance-aware adaptation. Experiments are carried out on 3 different scenarios of cross-domain detection and we achieve the state-of-the-art results against other approaches, showing the effectiveness of our proposed method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Unsupervised domain adaptationTransfer learningObject detection |
Paper # | PRMU2020-46 |
Date of Issue | 2020-12-10 (PRMU) |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2020/12/17(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Transfer learning and few shot learning |
Chair | Yoichi Sato(Univ. of Tokyo) |
Vice Chair | Akisato Kimura(NTT) / Masakazu Iwamura(Osaka Pref. Univ.) |
Secretary | Akisato Kimura(Mobility Technologies) / Masakazu Iwamura(Chubu Univ.) |
Assistant | Takashi Shibata(NTT) / Masashi Nishiyama(Tottori Univ.) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Hierarchical Contrastive Adaptation for Cross-Domain Object Detection |
Sub Title (in English) | |
Keyword(1) | Unsupervised domain adaptationTransfer learningObject detection |
1st Author's Name | Ziwei Deng |
1st Author's Affiliation | Lumada Data Science Lab. Hitachi, Ltd.(Hitachi) |
2nd Author's Name | Quan Kong |
2nd Author's Affiliation | Lumada Data Science Lab. Hitachi, Ltd.(Hitachi) |
3rd Author's Name | Naoto Akira |
3rd Author's Affiliation | Lumada Data Science Lab. Hitachi, Ltd.(Hitachi) |
4th Author's Name | Tomoaki Yoshinaga |
4th Author's Affiliation | Lumada Data Science Lab. Hitachi, Ltd.(Hitachi) |
Date | 2020-12-17 |
Paper # | PRMU2020-46 |
Volume (vol) | vol.120 |
Number (no) | PRMU-300 |
Page | pp.pp.47-52(PRMU), |
#Pages | 6 |
Date of Issue | 2020-12-10 (PRMU) |