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