Hyp2Former learns hierarchical semantic similarities in hyperbolic space among known categories so that unknown objects remain close to higher-level concepts and can be detected reliably.
In: Proceedings of the IEEE/CVF conference on computer vision and pattern recog- nition
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
Feedback Former improves cell image segmentation accuracy by feeding detailed feature maps back from near the output to lower transformer layers, outperforming non-feedback baselines with lower computational cost on three datasets.
citing papers explorer
-
Hyp2Former: Hierarchy-Aware Hyperbolic Embeddings for Open-Set Panoptic Segmentation
Hyp2Former learns hierarchical semantic similarities in hyperbolic space among known categories so that unknown objects remain close to higher-level concepts and can be detected reliably.
-
Accuracy Improvement of Cell Image Segmentation Using Feedback Former
Feedback Former improves cell image segmentation accuracy by feeding detailed feature maps back from near the output to lower transformer layers, outperforming non-feedback baselines with lower computational cost on three datasets.