mlsanityData to 14 Oct 2026

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

arXiv 2507.07460 ↗First posted 10 Jul 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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 textbftextitObjectomaly, 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, FPR95 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 46 references that are in the map. First posted on arXiv 10 Jul 2025.

Builds on

37 of 46 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2023Segment Anythingcited by 8,234
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  6. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  7. 2016Pyramid Scene Parsing Networkcited by 2,479
  8. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  9. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  10. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  11. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  12. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
25 more
  1. 2023Faster Segment Anything: Towards Lightweight SAM for Mobile Applicationscited by 352
  2. 2023Fast Segment Anythingcited by 290
  3. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  4. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  5. 2019Detecting the Unexpected via Image Resynthesiscited by 137
  6. 2022A Generalist Framework for Panoptic Segmentation of Images and Videoscited by 99
  7. 2022Anomaly Detection in Autonomous Driving: A Surveycited by 87
  8. 2022RbA: Segmenting Unknown Regions Rejected by Allcited by 67
  9. 2022Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentationcited by 55
  10. 2023Unmasking Anomalies in Road-Scene Segmentationcited by 45
  11. 2022DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognitioncited by 42
  12. 2023Maskomaly:Zero-Shot Mask Anomaly Segmentationcited by 34
  13. 2024Outlier detection by ensembling uncertainty with negative objectnesscited by 34
  14. 2023SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Processcited by 29
  15. 2023Quantification of Uncertainty with Adversarial Modelscited by 28
  16. 2024Open-World Semantic Segmentation Including Class Similaritycited by 24
  17. 2023Segment Every Out-of-Distribution Objectcited by 21
  18. 2024PixOOD: Pixel-Level Out-of-Distribution Detectioncited by 20
  19. 2024SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flowcited by 20
  20. 2022Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillationcited by 19
  21. 2023CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseencited by 15
  22. 20243D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillationcited by 13
  23. 2021A novel method of predictive collision risk area estimation for proactive pedestrian accident prevention system in urban surveillance infrastructurecited by 7
  24. 2025Towards Accurate Unified Anomaly Segmentationcited by 7
  25. 2024Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shiftscited by 5

Built on by

Not cited yet.