mlsanityData to 14 Oct 2026

Hierarchical Neural Collapse Detection Transformer for Class Incremental Object Detection

arXiv 2506.08562 ↗First posted 10 Jun 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, object detection models have witnessed notable performance improvements, particularly with transformer-based models. However, new objects frequently appear in the real world, requiring detection models to continually learn without suffering from catastrophic forgetting. Although Incremental Object Detection (IOD) has emerged to address this challenge, these existing models are still not practical due to their limited performance and prolonged inference time. In this paper, we introduce a novel framework for IOD, called Hier-DETR: Hierarchical Neural Collapse Detection Transformer, ensuring both efficiency and competitive performance by leveraging Neural Collapse for imbalance dataset and Hierarchical relation of classes' labels.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 40 references that are in the map. First posted on arXiv 10 Jun 2025.

Builds on

33 of 40 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  6. 2016Learning without Forgettingcited by 2,496
  7. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  8. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,319
  9. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 719
  10. 2018End-to-End Incremental Learningcited by 597
  11. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 573
  12. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 488
21 more
  1. 2021Conditional DETR for Fast Training Convergencecited by 424
  2. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 409
  3. 2021Towards Open World Object Detectioncited by 297
  4. 2019Maintaining Discrimination and Fairness in Class Incremental Learningcited by 283
  5. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 274
  6. 2017No Fuss Distance Metric Learning using Proxiescited by 226
  7. 2020Mnemonics Training: Multi-Class Incremental Learning without Forgettingcited by 221
  8. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  9. 2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learningcited by 116
  10. 2022Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?cited by 100
  11. 2022Memory Replay with Data Compression for Continual Learningcited by 82
  12. 2022Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillationcited by 72
  13. 2020Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNNcited by 61
  14. 2023Continual Detection Transformer for Incremental Object Detectioncited by 59
  15. 2019The Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scalecited by 50
  16. 2024SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detectioncited by 44
  17. 2023Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Datacited by 40
  18. 2021Multi-View Correlation Distillation for Incremental Object Detectioncited by 36
  19. 2020SID: Incremental Learning for Anchor-Free Object Detection via Selective and Inter-Related Distillationcited by 33
  20. 2024RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervisioncited by 32
  21. 2020Lifelong Object Detectioncited by 25

Built on by

Not cited yet.