Discovering class-specific pixels for weakly-supervised semantic segmentation
We propose an approach to discover class-specific pixels for the weakly-supervised semantic segmentation task. We show that properly combining saliency and attention maps allows us to obtain reliable cues capable of significantly boosting the performance. First, we propose a simple yet powerful hierar...
Asıl Yazarlar: | Chaudhry, A, Dokania, PK, Torr, PHS |
---|---|
Materyal Türü: | Conference item |
Dil: | English |
Baskı/Yayın Bilgisi: |
British Machine Vision Association
2017
|
Benzer Materyaller
-
Bottom-up top-down cues for weakly-supervised semantic segmentation
Yazar:: Hou, Q, ve diğerleri
Baskı/Yayın Bilgisi: (2018) -
Addressing Noisy Pixels in Weakly Supervised Semantic Segmentation with Weights Assigned
Yazar:: Feng Qian, ve diğerleri
Baskı/Yayın Bilgisi: (2024-08-01) -
Clustering-Guided Class Activation for Weakly Supervised Semantic Segmentation
Yazar:: Yeong Woo Kim, ve diğerleri
Baskı/Yayın Bilgisi: (2024-01-01) -
RSS-Net: weakly-supervised multi-class semantic segmentation with FMCW radar
Yazar:: Kaul, P, ve diğerleri
Baskı/Yayın Bilgisi: (2021) -
Continual learning in low-rank orthogonal subspaces
Yazar:: Chaudhry, A, ve diğerleri
Baskı/Yayın Bilgisi: (2020)