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...
Autori principali: | Chaudhry, A, Dokania, PK, Torr, PHS |
---|---|
Natura: | Conference item |
Lingua: | English |
Pubblicazione: |
British Machine Vision Association
2017
|
Documenti analoghi
Documenti analoghi
-
Bottom-up top-down cues for weakly-supervised semantic segmentation
di: Hou, Q, et al.
Pubblicazione: (2018) -
Addressing Noisy Pixels in Weakly Supervised Semantic Segmentation with Weights Assigned
di: Feng Qian, et al.
Pubblicazione: (2024-08-01) -
Clustering-Guided Class Activation for Weakly Supervised Semantic Segmentation
di: Yeong Woo Kim, et al.
Pubblicazione: (2024-01-01) -
RSS-Net: weakly-supervised multi-class semantic segmentation with FMCW radar
di: Kaul, P, et al.
Pubblicazione: (2021) -
Continual learning in low-rank orthogonal subspaces
di: Chaudhry, A, et al.
Pubblicazione: (2020)