mlsanityData to 7 Oct 2026

Expanding Low-Density Latent Regions for Open-Set Object Detection

arXiv 2203.14911 ↗First posted 28 Mar 2022cs.CVcited by 38

Not on the map. Why?

Abstract (arXiv)

Modern object detectors have achieved impressive progress under the close-set setup. However, open-set object detection (OSOD) remains challenging since objects of unknown categories are often misclassified to existing known classes. In this work, we propose to identify unknown objects by separating high/low-density regions in the latent space, based on the consensus that unknown objects are usually distributed in low-density latent regions. As traditional threshold-based methods only maintain limited low-density regions, which cannot cover all unknown objects, we present a novel Open-set Detector (OpenDet) with expanded low-density regions. To this aim, we equip OpenDet with two learners, Contrastive Feature Learner (CFL) and Unknown Probability Learner (UPL). CFL performs instance-level contrastive learning to encourage compact features of known classes, leaving more low-density regions for unknown classes; UPL optimizes unknown probability based on the uncertainty of predictions, which further divides more low-density regions around the cluster of known classes. Thus, unknown objects in low-density regions can be easily identified with the learned unknown probability. Extensive experiments demonstrate that our method can significantly improve the OSOD performance, e.g., OpenDet reduces the Absolute Open-Set Errors by 25%-35% on six OSOD benchmarks. Code is available at: https://github.com/csuhan/opendet2.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 43 of its 55 references that are in the map. First posted on arXiv 28 Mar 2022.

Builds on

43 of 55 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  10. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  11. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  12. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
31 more
  1. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  2. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  3. 2020Supervised Contrastive Learningcited by 2,803
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  5. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  6. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  7. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  8. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  9. 2015Towards Open Set Deep Networkscited by 533
  10. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  11. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  12. 2021Towards Open World Object Detectioncited by 297
  13. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  14. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  15. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  16. 2014Towards Open World Recognitioncited by 226
  17. 2021Parametric Contrastive Learningcited by 217
  18. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  19. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  20. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  21. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  22. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  23. 2021Contrastive Learning based Hybrid Networks for Long-Tailed Image Classificationcited by 130
  24. 2021Learning Placeholders for Open-Set Recognitioncited by 121
  25. 2020Learning Open Set Network with Discriminative Reciprocal Pointscited by 115
  26. 2017Dropout Sampling for Robust Object Detection in Open-Set Conditionscited by 112
  27. 2020Conditional Gaussian Distribution Learning for Open Set Recognitioncited by 104
  28. 2018Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detectioncited by 51
  29. 2021Exemplar-Based Open-Set Panoptic Segmentation Networkcited by 37
  30. 2017Sparse Representation-based Open Set Recognitioncited by 36
  31. 2020Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networkscited by 31

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 10; 2024: 12; 2025: 5; 2026: 6.

38 papers.

Sort:

By area:

  1. 2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
  2. 2023Contrastive Conditional Latent Diffusion for Audio-visual Segmentationcited by 30
  3. 2024Open-Set Recognition in the Age of Vision-Language Modelscited by 13
  4. 2023Activate and Reject: Towards Safe Domain Generalization under Category Shiftcited by 9
  5. 2022Dual Decision Improves Open-Set Panoptic Segmentationcited by 8
  6. 2022Towards Generalized Few-Shot Open-Set Object Detectioncited by 8
  7. 2022Open-Set Object Detection Using Classification-free Object Proposal and Instance-level Contrastive Learningcited by 7
  8. 2023Unsupervised Recognition of Unknown Objects for Open-World Object Detectioncited by 6
  9. 2025Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalancecited by 6
  10. 2023USD: Unknown Sensitive Detector Empowered by Decoupled Objectness and Segment Anything Modelcited by 4
  11. 2023Rethinking Polyp Segmentation from an Out-of-Distribution Perspectivecited by 4
  12. 2024Hierarchical Visual Categories Modeling: A Joint Representation Learning and Density Estimation Framework for Out-of-Distribution Detectioncited by 4
26 more
  1. 2024Open-Vocabulary Object Detection with Meta Prompt Representation and Instance Contrastive Optimizationcited by 3
  2. 2024Boosting Few-Shot Open-Set Object Detection via Prompt Learning and Robust Decision Boundarycited by 3
  3. 2025Deep Learning for Sports Video Event Detection: Tasks, Datasets, Methods, and Challengescited by 3
  4. 2022Tunable Hybrid Proposal Networks for the Open Worldcited by 2
  5. 2024UADet: A Remarkably Simple Yet Effective Uncertainty-Aware Open-Set Object Detection Frameworkcited by 2
  6. 2022Rethinking Open-Set Object Detection: Issues, a New Formulation, and Taxonomycited by 1
  7. 2023Generalized Open-World Semi-Supervised Object Detectioncited by 1
  8. 2024O1O: Grouping of Known Classes to Identify Unknown Objects as Odd-One-Outcited by 1
  9. 2024Open-Set Object Detection By Aligning Known Class Representationscited by 1
  10. 2026DDStereo: Efficient Dual Decoder Transformers for Stereo 3D Road Anomaly Detectioncited by 1
  11. 2023Online Open-set Semi-supervised Object Detection with Dual Competing Headcited by 0
  12. 2023Detecting Out-of-distribution Objects Using Neuron Activation Patternscited by 0
  13. 2023Incremental Object Detection with CLIPcited by 0
  14. 2024Wasserstein Distance-based Expansion of Low-Density Latent Regions for Unknown Class Detectioncited by 0
  15. 2024YOLOOC: YOLO-based Open-Class Incremental Object Detection with Novel Class Discoverycited by 0
  16. 2024OSR-ViT: A Simple and Modular Framework for Open-Set Object Detection and Discoverycited by 0
  17. 2024Class-balanced Open-set Semi-supervised Object Detection for Medical Imagescited by 0
  18. 2024Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detectioncited by 0
  19. 2025FindMeIfYouCan: Bringing Open Set metrics to textitnear , textitfar and textitfarther Out-of-Distribution Object Detectioncited by 0
  20. 2025Adapt, But Don't Forget: Fine-Tuning and Contrastive Routing for Lane Detection under Distribution Shiftcited by 0
  21. 2025Three-Way Open-Set Detection for Robust Autonomous Navigationcited by 0
  22. 2026OOVDet: Low-Density Prior Learning for Zero-Shot Out-of-Vocabulary Object Detectioncited by 0
  23. 2026Towards Adaptive Open-Set Object Detection via Category-Level Collaboration Knowledge Miningcited by 0
  24. 2026Beyond Known Objects: A Novel Framework for Open-Set Object Detection using Negative-Aware Normcited by 0
  25. 2026Training-Free Open-Vocabulary Visual Grounding for Remote Sensing Images and Videoscited by 0
  26. 2026WALDO: One-Shot Exemplar-Conditioned Object Detection in Cluttered Scenescited by 0