Redefining Instance Matching: A Unified Framework for Part-Aware Matching in Panoptic Segmentation Evaluation

• URL: http://arxiv.org/abs/2605.31094v1
• Date: Fri, 29 May 2026 10:04:25 GMT
• Title: Redefining Instance Matching: A Unified Framework for Part-Aware Matching in Panoptic Segmentation Evaluation
• Abstract summary: We recast segment matching as a constrained bipartite assignment problem.<n>We show that the framework extends naturally to part-aware panoptic segmentation.<n>We release a unified open-source package built on Panoptica.
• Score: 4.312173899947468
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Panoptic Quality (PQ) metric is the standard for jointly evaluating instance and semantic segmentation. However, its original definition relies on a One-to-One matching between predicted and ground truth segments, which is only straightforward when the IoU threshold exceeds 0.5. Below 0.5, multiple matching strategies emerge in a poorly explored problem space. We systematically elucidate this space by recasting segment matching as a constrained bipartite assignment problem. Independently bounding the prediction- and ground-truth-side degrees yields four matching strategies: One-to-One, Many-to-One, One-to-Many, and Many-to-Many. We show that the first three are well-defined within the PQ framework, while Many-to-Many falls outside it. These strategies become relevant when instances are fragmented, adjacent objects are difficult to delineate, or annotations are noisy. Central to our framework is a vertex-based accounting of TP, FN, and FP, anchored to ground truth and predicted segments rather than to matching edges. We further show that the framework extends naturally to part-aware panoptic segmentation, and we explore part-aware evaluation on biomedical data. Across configurable case studies we report how different combinations of thresholds and matching strategies behave in practice. We release a unified open-source package built on Panoptica. It exposes Voronoi-based region-wise analysis, part-aware evaluation, and Area Under Threshold Curve computations as configurable options.

Related papers

• MORI-Seg: Learning Morphological Geometry for Instance Segmentation without Instance Annotations [8.822301906283052]
  We propose MORI-Seg, a deep learning framework that enables instance segmentation without requiring instance-level annotations.<n>Instead of splitting or instance supervision, MORI-Seg learns morphology-aware geometric representations directly from semantic masks.<n>Under semantic-only supervision, MORI-Seg decomposes connected semantic regions into distinct instance masks in an end-to-end manner.
  arXiv  Detail & Related papers  (2026-05-27T10:11:30Z)
• ClipTBP: Clip-Pair based Temporal Boundary Prediction with Boundary-Aware Learning for Moment Retrieval [56.989259812432]
  We propose ClipTBP, a clip-pair temporal boundary prediction framework based on boundary-aware learning.<n>We show that ClipTBP consistently improves performance when applied to various existing models and demonstrates more robust boundary prediction performance even in ambiguous query scenarios.
  arXiv  Detail & Related papers  (2026-04-30T08:41:41Z)
• When F1 Fails: Granularity-Aware Evaluation for Dialogue Topic Segmentation [0.0]
  This paper introduces an evaluation framework that reports boundary density and segment alignment diagnostics (purity and coverage) alongside window-tolerant F1 (W-F1)<n>By separating boundary scoring from boundary selection, we evaluate segmentation quality across density regimes rather than at a single operating point.
  arXiv  Detail & Related papers  (2025-12-18T21:29:43Z)
• Harnessing Group-Oriented Consistency Constraints for Semi-Supervised Semantic Segmentation in CdZnTe Semiconductors [71.44213719783703]
  Intra-group Consistency Augmentation Framework (ICAF) developed to label Cadmium Zinc Telluride (CdZnTe) semiconductor images.<n>ICAF consists of two key modules, the View Augmentation Module (VAM) and the View Correction Module (VCM)<n>ICAF achieves a 70.6% mIoU on the CdZnTe dataset using only 2 group-annotated data.
  arXiv  Detail & Related papers  (2025-08-18T09:40:36Z)
• Split Matching for Inductive Zero-shot Semantic Segmentation [56.47556212515178]
  Zero-shot Semantic (ZSS) aims to segment categories that are not annotated during training.<n>We propose Split Matching (SM), a novel assignment strategy that decouples Hungarian matching into two components.<n>SM is the first to introduce decoupled Hungarian matching under the inductive ZSS setting, and achieves state-of-the-art performance on two standard benchmarks.
  arXiv  Detail & Related papers  (2025-05-08T07:56:30Z)
• BAISeg: Boundary Assisted Weakly Supervised Instance Segmentation [9.6046915661065]
  How to extract instance-level masks without instance-level supervision is the main challenge of weakly supervised instance segmentation (WSIS) Popular WSIS methods estimate a displacement field (DF) via learning inter-pixel relations and perform clustering to identify instances. We propose Boundary-Assisted Instance (BAISeg), which is a novel paradigm for WSIS that realizes instance segmentation with pixel-level annotations.
  arXiv  Detail & Related papers  (2024-05-27T15:14:09Z)
• Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation [63.910211095033596]
  Few-shot segmentation aims to segment unseen-class objects given only a handful of densely labeled samples. We propose a simple yet versatile framework in the spirit of divide-and-conquer. Our proposed approach, named divide-and-conquer proxies (DCP), allows for the development of appropriate and reliable information.
  arXiv  Detail & Related papers  (2022-04-21T06:21:14Z)
• Proposal-free Lidar Panoptic Segmentation with Pillar-level Affinity [10.378476897786571]
  We jointly optimize semantic segmentation and class-agnostic instance classification in a single network. Our experiments on nuScenes dataset show that our approach outperforms previous proposal-free methods.
  arXiv  Detail & Related papers  (2022-04-19T08:39:37Z)
• PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation [96.76882806139251]
  We propose a point-wise affinity propagation module based on the Feature Pyramid Network (FPN) framework, named PointFlow. Rather than dense affinity learning, a sparse affinity map is generated upon selected points between the adjacent features. Experimental results on three different aerial segmentation datasets suggest that the proposed method is more effective and efficient than state-of-the-art general semantic segmentation methods.
  arXiv  Detail & Related papers  (2021-03-11T09:42:32Z)
• Deep Affinity Net: Instance Segmentation via Affinity [48.498706304017674]
  Deep Affinity Net is an effective affinity-based approach accompanied with a new graph partitioning algorithm Cascade-GAEC. It achieves the best single-shot result as well as the fastest running time among all affinity-based models. It also outperforms the region-based method Mask R-CNN.
  arXiv  Detail & Related papers  (2020-03-15T15:22:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.