mlsanityData to 7 Oct 2026

DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection

arXiv 2503.09271 ↗First posted 12 Mar 2025cs.CV cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Open-Vocabulary object detectors can generalize to an unrestricted set of categories through simple textual prompting. However, adapting these models to rare classes or reinforcing their abilities on multiple specialized domains remains essential. While recent methods rely on monolithic adaptation strategies with a single set of weights, we embrace modular deep learning. We introduce DitHub, a framework designed to build and maintain a library of efficient adaptation modules. Inspired by Version Control Systems, DitHub manages expert modules as branches that can be fetched and merged as needed. This modular approach allows us to conduct an in-depth exploration of the compositional properties of adaptation modules, marking the first such study in Object Detection. Our method achieves state-of-the-art performance on the ODinW-13 benchmark and ODinW-O, a newly introduced benchmark designed to assess class reappearance. For more details, visit our project page: https://aimagelab.github.io/DitHub/

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 47 of its 62 references that are in the map. First posted on arXiv 12 Mar 2025.

Builds on

47 of 62 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  8. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  9. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  10. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  11. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  12. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
35 more
  1. 2021Grounded Language-Image Pre-trainingcited by 1,147
  2. 2022Editing Models with Task Arithmeticcited by 1,076
  3. 2021Learning to Prompt for Continual Learningcited by 938
  4. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  5. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
  6. 2023TIES-Merging: Resolving Interference When Merging Modelscited by 795
  7. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  8. 2022DualPrompt: Complementary Prompting for Rehearsal-free Continual Learningcited by 635
  9. 2019Linear Mode Connectivity and the Lottery Ticket Hypothesiscited by 627
  10. 2021ImageNet-21K Pretraining for the Massescited by 607
  11. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  12. 2022CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learningcited by 446
  13. 2021Conditional DETR for Fast Training Convergencecited by 422
  14. 2023LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Compositioncited by 359
  15. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  16. 2023AdaMerging: Adaptive Model Merging for Multi-Task Learningcited by 248
  17. 2022Open-Vocabulary DETR with Conditional Matchingcited by 220
  18. 2023Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Modelscited by 218
  19. 2024Mixture of LoRA Expertscited by 179
  20. 2023Composing Parameter-Efficient Modules with Arithmetic Operationscited by 155
  21. 2020Linear Mode Connectivity in Multitask and Continual Learningcited by 144
  22. 2022ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Modelscited by 141
  23. 2021OW-DETR: Open-world Detection Transformercited by 129
  24. 2022Class-Incremental Continual Learning into the eXtended DER-versecited by 121
  25. 2023Modular Deep Learningcited by 82
  26. 2023Continual Detection Transformer for Incremental Object Detectioncited by 59
  27. 2023Weighted Ensemble Models Are Strong Continual Learnerscited by 41
  28. 2023UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modelingcited by 40
  29. 2022Exploring Mode Connectivity for Pre-trained Language Modelscited by 26
  30. 2024Closed-form merging of parameter-efficient modules for Federated Continual Learningcited by 22
  31. 2024A Second-Order Perspective on Model Compositionality and Incremental Learningcited by 18
  32. 2024Zero-shot Generalizable Incremental Learning for Vision-Language Object Detectioncited by 15
  33. 2022Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learningcited by 14
  34. 2024Towards RAW Object Detection in Diverse Conditionscited by 9
  35. 2024Is Multiple Object Tracking a Matter of Specialization?cited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025PixelArena: A benchmark for Pixel-Precision Visual Intelligencecited by 1
  2. 2026ABRA: Teleporting Fine-Tuned Knowledge Across Domains for Open-Vocabulary Object Detectioncited by 0
  3. 2026MECAIL: Communication-Aware Incremental Learning for Object Detection with 14.6 KB Spatiotemporal Expertscited by 0