Box2Seg: Attention weighted loss and discriminative feature learning for weakly supervised segmentation
We propose a weakly supervised approach to semantic segmentation using bounding box annotations. Bounding boxes are treated as noisy labels for the foreground objects. We predict a per-class attention map that saliently guides the per-pixel cross entropy loss to focus on foreground pixels and refine...
Main Authors: | Kulharia, V, Chandra, S, Agrawal, A, Torr, PHS, Tyagi, A |
---|---|
格式: | Conference item |
語言: | English |
出版: |
Springer International Publishing
2020
|
相似書籍
-
Discovering class-specific pixels for weakly-supervised semantic segmentation
由: Chaudhry, A, et al.
出版: (2017) -
SegPGD: an effective and efficient adversarial attack for evaluating and boosting segmentation robustness
由: Gu, J, et al.
出版: (2022) -
Weakly- and semi-supervised panoptic segmentation
由: Li, Q, et al.
出版: (2018) -
IARS SegNet: Interpretable Attention Residual Skip Connection SegNet for Melanoma Segmentation
由: V. Shankara Narayanan, et al.
出版: (2024-01-01) -
Polarized Attention Weak Supervised Semantic Segmentation Network
由: Min Dai, et al.
出版: (2024-01-01)