Objectomaly: Objectness-Aware Refinement for OoD Segmentation with Structural Consistency and Boundary Precision

• URL: http://arxiv.org/abs/2507.07460v2
• Date: Fri, 11 Jul 2025 04:12:46 GMT
• Title: Objectomaly: Objectness-Aware Refinement for OoD Segmentation with Structural Consistency and Boundary Precision
• Authors: Jeonghoon Song, Sunghun Kim, Jaegyun Im, Byeongjoon Noh,
• Abstract summary: Out-of-Distribution (OoD) segmentation is critical for safety-sensitive applications like autonomous driving.<n>Existing mask-based methods often suffer from boundary imprecision, inconsistent anomaly scores within objects, and false positives from background noise.<n>We propose textbftextitObjectomaly, an objectness-aware refinement framework that incorporates object-level priors.
• Score: 1.2036459029967645
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Out-of-Distribution (OoD) segmentation is critical for safety-sensitive applications like autonomous driving. However, existing mask-based methods often suffer from boundary imprecision, inconsistent anomaly scores within objects, and false positives from background noise. We propose \textbf{\textit{Objectomaly}}, an objectness-aware refinement framework that incorporates object-level priors. Objectomaly consists of three stages: (1) Coarse Anomaly Scoring (CAS) using an existing OoD backbone, (2) Objectness-Aware Score Calibration (OASC) leveraging SAM-generated instance masks for object-level score normalization, and (3) Meticulous Boundary Precision (MBP) applying Laplacian filtering and Gaussian smoothing for contour refinement. Objectomaly achieves state-of-the-art performance on key OoD segmentation benchmarks, including SMIYC AnomalyTrack/ObstacleTrack and RoadAnomaly, improving both pixel-level (AuPRC up to 96.99, FPR$_{95}$ down to 0.07) and component-level (F1$-$score up to 83.44) metrics. Ablation studies and qualitative results on real-world driving videos further validate the robustness and generalizability of our method. Code will be released upon publication.

Related papers

• Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting [86.15347226865826]
  We design a new end-to-end object-aware lifting approach, named Unified-Lift.<n>We augment each Gaussian point with an additional Gaussian-level feature learned using a contrastive loss to encode instance information.<n>We conduct experiments on three benchmarks: LERF-Masked, Replica, and Messy Rooms.
  arXiv  Detail & Related papers  (2025-03-18T08:42:23Z)
• Mitigating Hallucinations in YOLO-based Object Detection Models: A Revisit to Out-of-Distribution Detection [8.206992765692535]
  This paper studies the underlying reasons for performance bottlenecks and proposes a methodology to improve performance fundamentally.<n>By developing a methodology to carefully synthesize an OoD dataset that semantically resembles the objects to be detected, we achieve a 88% reduction in overall hallucination error.
  arXiv  Detail & Related papers  (2025-03-10T13:42:41Z)
• PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection [65.84604846389624]
  We propose PointOBB-v3, a stronger single point-supervised OOD framework.<n>It generates pseudo rotated boxes without additional priors and incorporates support for the end-to-end paradigm.<n>Our method achieves an average improvement in accuracy of 3.56% in comparison to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-01-23T18:18:15Z)
• Bridge the Points: Graph-based Few-shot Segment Anything Semantically [79.1519244940518]
  Recent advancements in pre-training techniques have enhanced the capabilities of vision foundation models. Recent studies extend the SAM to Few-shot Semantic segmentation (FSS) We propose a simple yet effective approach based on graph analysis.
  arXiv  Detail & Related papers  (2024-10-09T15:02:28Z)
• Segment Every Out-of-Distribution Object [24.495734304922244]
  This paper introduces a method to convert anomaly textbfScore textbfTo segmentation textbfMask, called S2M, a simple and effective framework for OoD detection in semantic segmentation. By transforming anomaly scores into prompts for a promptable segmentation model, S2M eliminates the need for threshold selection.
  arXiv  Detail & Related papers  (2023-11-27T18:20:03Z)
• Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling [38.07637524378327]
  Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection. Existing DA methods suffer from a substantial drop in performance when applied to a multi-class training setting. We propose a novel ReDB framework tailored for learning to detect all classes at once.
  arXiv  Detail & Related papers  (2023-07-16T04:34:11Z)
• ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection [55.291579862817656]
  Existing oriented object detection methods commonly use metric AP$_50$ to measure the performance of the model. We argue that AP$_50$ is inherently unsuitable for oriented object detection due to its large tolerance in angle deviation. We propose an Aspect Ratio Sensitive Oriented Object Detector with Transformer, termed ARS-DETR, which exhibits a competitive performance.
  arXiv  Detail & Related papers  (2023-03-09T02:20:56Z)
• A Tri-Layer Plugin to Improve Occluded Detection [100.99802831241583]
  We propose a simple '' module for the detection head of two-stage object detectors to improve the recall of partially occluded objects. The module predicts a tri-layer of segmentation masks for the target object, the occluder and the occludee, and by doing so is able to better predict the mask of the target object. We also establish a COCO evaluation dataset to measure the recall performance of partially occluded and separated objects.
  arXiv  Detail & Related papers  (2022-10-18T17:59:51Z)
• Topologically Persistent Features-based Object Recognition in Cluttered Indoor Environments [1.2691047660244335]
  Recognition of occluded objects in unseen indoor environments is a challenging problem for mobile robots. This work proposes a new slicing-based topological descriptor that captures the 3D shape of object point clouds. It yields similarities between the descriptors of the occluded and the corresponding unoccluded objects, enabling object unity-based recognition.
  arXiv  Detail & Related papers  (2022-05-16T07:01:16Z)
• SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection [78.90102636266276]
  We propose a novel set abstraction method named Semantics-Augmented Set Abstraction (SASA) Based on the estimated point-wise foreground scores, we then propose a semantics-guided point sampling algorithm to help retain more important foreground points during down-sampling. In practice, SASA shows to be effective in identifying valuable points related to foreground objects and improving feature learning for point-based 3D detection.
  arXiv  Detail & Related papers  (2022-01-06T08:54:47Z)
• Shallow Feature Matters for Weakly Supervised Object Localization [35.478997006168484]
  Weakly supervised object localization (WSOL) aims to localize objects by only utilizing image-level labels. Previous CAM-based methods did not take full advantage of the shallow features, despite their importance for WSOL. In this paper, we propose a simple but effective Shallow feature-aware Pseudo supervised Object localization (SPOL) model for accurate WSOL.
  arXiv  Detail & Related papers  (2021-08-02T13:16:48Z)

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.