Research map / Detection and segmentation / Open-set and few-shot detection
PatchPerPix for Instance Segmentation
Lisa Mais, Peter Hirsch, Dagmar Kainmueller
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add consensus affinity computation (ablation) | PatchPerPix (ppp+dec) · BBBC010 | avAP: avAP -0.176 when absent (MWS-Dense) | Improved |
| add patch selection by consensus score (ablation) | PatchPerPix (ppp+dec) · BBBC010 | avAP: avAP - 0.131 when absent | Improved |
| add thinning of the patch selection (ablation) | PatchPerPix (ppp+dec) · BBBC010 | avAP: 0.723 -> 0.727 | Improved |
| use decoder with increasing feature maps instead of standard U-Net (ablation) | ppp+dec · BBBC010 | avAP: 0.719 -> 0.727 | Improved |
| use mutex watershed instead of connected components for partitioning (ablation) | ppp+dec · BBBC010 | avAP: 0.723 -> 0.727 | No clear effect |
| replace separately trained autoencoder (ppp+ae) with joint decoder (ppp+dec) | PatchPerPix · BBBC010 | avAP: 0.617 -> 0.727 | Improved |
| use full U-Net encoder with decoder instead of sliding-window encoder-decoder (ed-ppp) | PatchPerPix · BBBC010 | avAP: 0.675 -> 0.727 | Improved |
| add decoder over raw patch prediction (ppp+dec vs ppp) | PatchPerPix · BBBC010 | avAP: 0.689 -> 0.727 | Improved |
| add decoder over raw patch prediction (ppp+dec vs ppp) | PatchPerPix · nuclei3d | avAP | No clear effect |
| use PatchPerPix consensus patch assembly instead of dense affinities with MWS (ablation) | PatchPerPix · ISBI 2012 EM | rRAND: 0.979112 -> 0.988290 | Improved |
| use PatchPerPix instead of MWS | ISBI 2012 EM segmentation · ISBI 2012 EM | rRAND: 0.987922 -> 0.988290 | Improved |
Closest papers by meaning
- Unsupervised Learning of Object-Centric Embeddings for Cell Instance Segmentation in Microscopy Images (ICCV 2023 · similarity 0.88)
- Object-Guided Instance Segmentation for Biological Images (AAAI 2020 · similarity 0.88)
- Sparse Object-Level Supervision for Instance Segmentation With Pixel Embeddings (CVPR 2022 · similarity 0.88)
- FISBe: A Real-World Benchmark Dataset for Instance Segmentation of Long-Range Thin Filamentous Structures (CVPR 2024 · similarity 0.86)
- Training-Free Dataset Pruning for Instance Segmentation (ICLR 2025 · similarity 0.85)
- Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking (CVPR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
