ScholarGate
Asisten
Machine learningDeep learning / NLP / CV

Deteksi Objek Berpengawasan Lemah

Deteksi Objek Berpengawasan Lemah (WSOD) melatih detektor objek hanya menggunakan label tingkat citra—yang menunjukkan kelas objek mana yang muncul dalam citra—tanpa memerlukan anotasi kotak pembatas yang mahal. Formulasi Pembelajaran Multi-Instansi (MIL) memungkinkan model untuk menemukan lokasi yang mungkin dari setiap kelas objek hanya dari sinyal klasifikasi, secara dramatis mengurangi biaya anotasi.

Buka di MethodMindSegeraVideoSegeraDownload slides

Baca metode selengkapnya

Khusus anggota

Masuk dengan akun gratis untuk membaca bagian ini.

Masuk

Method map

The neighbourhood of related methods — select a node to explore.

Sumber

  1. Bilen, H., & Vedaldi, A. (2016). Weakly supervised deep detection networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2846–2854. DOI: 10.1109/CVPR.2016.311
  2. Tang, P., Wang, X., Bai, X., & Liu, W. (2017). Multiple instance detection network with online instance classifier refinement. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2843–2851. DOI: 10.1109/cvpr.2017.326

Cara menyitasi halaman ini

ScholarGate. (2026, June 3). Weakly Supervised Object Detection (WSOD). ScholarGate. https://scholargate.app/id/deep-learning/weakly-supervised-object-detection

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Dirujuk oleh

ScholarGateWeakly Supervised Object Detection (Weakly Supervised Object Detection (WSOD)). Diakses 2026-06-15 dari https://scholargate.app/id/deep-learning/weakly-supervised-object-detection · Set data: https://doi.org/10.5281/zenodo.20539026