mlsanityData to 14 Oct 2026

SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds

arXiv 2506.13224 ↗First posted 16 Jun 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent advancements in deep learning have greatly enhanced 3D object recognition, but most models are limited to closed-set scenarios, unable to handle unknown samples in real-world applications. Open-set recognition (OSR) addresses this limitation by enabling models to both classify known classes and identify novel classes. However, current OSR methods rely on global features to differentiate known and unknown classes, treating the entire object uniformly and overlooking the varying semantic importance of its different parts. To address this gap, we propose Salience-Aware Structured Separation (SASep), which includes (i) a tunable semantic decomposition (TSD) module to semantically decompose objects into important and unimportant parts, (ii) a geometric synthesis strategy (GSS) to generate pseudo-unknown objects by combining these unimportant parts, and (iii) a synth-aided margin separation (SMS) module to enhance feature-level separation by expanding the feature distributions between classes. Together, these components improve both geometric and feature representations, enhancing the model's ability to effectively distinguish known and unknown classes. Experimental results show that SASep achieves superior performance in 3D OSR, outperforming existing state-of-the-art methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 44 references that are in the map. First posted on arXiv 16 Jun 2025.

Builds on

35 of 44 references.

References · 35

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2020Supervised Contrastive Learningcited by 2,829
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  8. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  9. 2020Point Transformercited by 1,470
  10. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  11. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  12. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
23 more
  1. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 724
  2. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  3. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  4. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  5. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  6. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  7. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  8. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  9. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  10. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  11. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  12. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  13. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  14. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  15. 2024Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Modelcited by 57
  16. 2019Octree guided CNN with Spherical Kernels for 3D Point Cloudscited by 50
  17. 2021Energy-Based Open-World Uncertainty Modeling for Confidence Calibrationcited by 46
  18. 2023Toward Unsupervised 3D Point Cloud Anomaly Detection using Variational Autoencodercited by 18
  19. 2021Detecting Anomalies in Semantic Segmentation with Prototypescited by 13
  20. 20223DOS: Towards 3D Open Set Learning -- Benchmarking and Understanding Semantic Novelty Detection on Point Cloudscited by 11
  21. 2022PointCaM: Cut-and-Mix for Open-Set Point Cloud Learningcited by 11
  22. 2024Exploring Diverse Representations for Open Set Recognitioncited by 8
  23. 2020Empowering Knowledge Distillation via Open Set Recognition for Robust 3D Point Cloud Classificationcited by 6

Built on by

Not cited yet.