Instance-Invariant Domain Adaptive Object Detection Via Progressive Disentanglement | PERPUSTAKAAN UNIVERSITAS KATOLIK PARAHYANGAN

Pencarian berdasarkan :

Pencarian terakhir:

Text

Instance-Invariant Domain Adaptive Object Detection Via Progressive Disentanglement

Wu, Aming - Nama Orang; Yang, Yi - Nama Orang; Han, Yahong - Nama Orang; Zhu, Linchao - Nama Orang;

Most state-of-the-art methods of object detection suffer from poor generalization ability when the training and test data are from different domains. To address this problem, previous methods mainly explore to align distribution between source and target domains, which may neglect the impact of the domain-specific information existing in the aligned features. Besides, when transferring detection ability across different domains, it is important to extract the instance-level features that are domain-invariant. To this end, we explore to extract instance-invariant features by disentangling the domain-invariant features from the domain-specific features. Particularly, a progressive disentangled mechanism is proposed to decompose domain-invariant and domain-specific features, which consists of a base disentangled layer and a progressive disentangled layer. Then, with the help of Region Proposal Network (RPN), the instance-invariant features are extracted based on the output of the progressive disentangled layer. Finally, to enhance the disentangled ability, we design a detached optimization to train our model in an end-to-end fashion. Experimental results on four domain-shift scenes show our method is separately 2.3, 3.6, 4.0, and 2.0 percent higher than the baseline method. Meanwhile, visualization analysis demonstrates that our model owns well disentangled ability.

Ketersediaan

Barcode		Tipe Koleksi	Nomor Panggil	Lokasi	Status
art143647	null	Artikel		Gdg9-Lt3	Tersedia namun tidak untuk dipinjamkan - No Loan

Informasi Detail

Judul Seri: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.44 No.8 August 2022
No. Panggil: -
Penerbit: : .,
Deskripsi Fisik: p. 4178-4193
Bahasa: English
ISBN/ISSN: -
Klasifikasi: NONE
Tipe Isi: -
Tipe Media: -
Tipe Pembawa: -
Edisi: -
Subjek: DOMAIN ADAPTIVE OBJECT DETECTION
PROGRESSIVE DISENTANGLEMENT
DETACHED OPTIMIZATION
INSTANCE-INVARIANT FEATURES
Info Detail Spesifik: DOI: 10.1109/TPAMI.2021.3060446
Pernyataan Tanggungjawab: Aming Wu, Yahong Han, Linchao Zhu, Yi Yang

Versi lain/terkait

Tidak tersedia versi lain

Lampiran Berkas

Tidak Ada Data

Komentar

Anda harus masuk sebelum memberikan komentar