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...
主要な著者: | Kulharia, V, Chandra, S, Agrawal, A, Torr, PHS, Tyagi, A |
---|---|
フォーマット: | Conference item |
言語: | English |
出版事項: |
Springer International Publishing
2020
|
類似資料
-
Discovering class-specific pixels for weakly-supervised semantic segmentation
著者:: Chaudhry, A, 等
出版事項: (2017) -
SegPGD: an effective and efficient adversarial attack for evaluating and boosting segmentation robustness
著者:: Gu, J, 等
出版事項: (2022) -
Weakly- and semi-supervised panoptic segmentation
著者:: Li, Q, 等
出版事項: (2018) -
IARS SegNet: Interpretable Attention Residual Skip Connection SegNet for Melanoma Segmentation
著者:: V. Shankara Narayanan, 等
出版事項: (2024-01-01) -
Polarized Attention Weak Supervised Semantic Segmentation Network
著者:: Min Dai, 等
出版事項: (2024-01-01)