Semantic Bottleneck Networks add interpretable semantic concept layers to deep networks, recovering SOTA segmentation performance with drastic channel reduction and enabling failure interpretation at over 99% accuracy for most outputs.
The cityscapes dataset for semantic urban scene understanding
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 4roles
dataset 1polarities
background 1representative citing papers
A two-stage pipeline generates pseudo masks from image-level labels to train Mask R-CNN, achieving state-of-the-art results on PASCAL VOC 2012 for weakly supervised instance segmentation.
Virtual KITTI 2 supplies synthetic clones of real KITTI driving sequences with added weather and camera variants and multi-modal ground-truth annotations for autonomous driving vision research.
Dilated affinity is jointly predicted with segmentation labels to strengthen features and support efficient label propagation refinement on benchmark datasets.
citing papers explorer
-
Interpretability Beyond Classification Output: Semantic Bottleneck Networks
Semantic Bottleneck Networks add interpretable semantic concept layers to deep networks, recovering SOTA segmentation performance with drastic channel reduction and enabling failure interpretation at over 99% accuracy for most outputs.
-
Where are the Masks: Instance Segmentation with Image-level Supervision
A two-stage pipeline generates pseudo masks from image-level labels to train Mask R-CNN, achieving state-of-the-art results on PASCAL VOC 2012 for weakly supervised instance segmentation.
-
Improving Semantic Segmentation via Dilated Affinity
Dilated affinity is jointly predicted with segmentation labels to strengthen features and support efficient label propagation refinement on benchmark datasets.