CAFE benchmark reveals that promptable segmentation models often produce correct masks for misleading prompts, showing a gap between localization accuracy and true concept understanding.
One-shot instance segmentation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
We tackle the problem of one-shot instance segmentation: Given an example image of a novel, previously unknown object category, find and segment all objects of this category within a complex scene. To address this challenging new task, we propose Siamese Mask R-CNN. It extends Mask R-CNN by a Siamese backbone encoding both reference image and scene, allowing it to target detection and segmentation towards the reference category. We demonstrate empirical results on MS Coco highlighting challenges of the one-shot setting: while transferring knowledge about instance segmentation to novel object categories works very well, targeting the detection network towards the reference category appears to be more difficult. Our work provides a first strong baseline for one-shot instance segmentation and will hopefully inspire further research into more powerful and flexible scene analysis algorithms. Code is available at: https://github.com/bethgelab/siamese-mask-rcnn
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3years
2026 3roles
background 1polarities
background 1representative citing papers
TSMa and SHARe lift COCO few-shot object detection by +10.1 nAP over prior prototype methods by enlarging class margins and refining boxes hierarchically.
Boundary-by-Mask uses a foundation-model encoder plus SDF head to predict boundary-aware distance maps from few mask examples, enabling instance segmentation on low-texture industrial objects via SDF-to-mask reconstruction.
citing papers explorer
-
From Pixels to Concepts: Do Segmentation Models Understand What They Segment?
CAFE benchmark reveals that promptable segmentation models often produce correct masks for misleading prompts, showing a gap between localization accuracy and true concept understanding.
-
Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection
TSMa and SHARe lift COCO few-shot object detection by +10.1 nAP over prior prototype methods by enlarging class margins and refining boxes hierarchically.
-
Boundary-by-Mask: Few-Shot Instance Segmentation with Mask-Conditioned Boundary Learning for Texture-Poor Industrial Parts
Boundary-by-Mask uses a foundation-model encoder plus SDF head to predict boundary-aware distance maps from few mask examples, enabling instance segmentation on low-texture industrial objects via SDF-to-mask reconstruction.