mlsanityData to 7 Oct 2026

Zero-shot Generalizable Incremental Learning for Vision-Language Object Detection

arXiv 2403.01680 ↗First posted 4 Mar 2024cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

This paper presents Incremental Vision-Language Object Detection (IVLOD), a novel learning task designed to incrementally adapt pre-trained Vision-Language Object Detection Models (VLODMs) to various specialized domains, while simultaneously preserving their zero-shot generalization capabilities for the generalized domain. To address this new challenge, we present the Zero-interference Reparameterizable Adaptation (ZiRa), a novel method that introduces Zero-interference Loss and reparameterization techniques to tackle IVLOD without incurring additional inference costs or a significant increase in memory usage. Comprehensive experiments on COCO and ODinW-13 datasets demonstrate that ZiRa effectively safeguards the zero-shot generalization ability of VLODMs while continuously adapting to new tasks. Specifically, after training on ODinW-13 datasets, ZiRa exhibits superior performance compared to CL-DETR and iDETR, boosting zero-shot generalizability by substantial 13.91 and 8.74 AP, respectively.Our code is available at https://github.com/JarintotionDin/ZiRaGroundingDINO.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 37 of its 46 references that are in the map. First posted on arXiv 4 Mar 2024.

Builds on

37 of 46 references.

References · 37

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  7. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  8. 2016Learning without Forgettingcited by 2,465
  9. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  10. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  11. 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,310
  12. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
25 more
  1. 2021Grounded Language-Image Pre-trainingcited by 1,147
  2. 2021Learning to Prompt for Continual Learningcited by 938
  3. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  4. 2015Generation and Comprehension of Unambiguous Object Descriptionscited by 897
  5. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  6. 2019Deep Modular Co-Attention Networks for Visual Question Answeringcited by 338
  7. 2021Towards Open World Object Detectioncited by 297
  8. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  9. 2022GLIPv2: Unifying Localization and Vision-Language Understandingcited by 275
  10. 2022S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learningcited by 246
  11. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  12. 2020Modeling the Background for Incremental Learning in Semantic Segmentationcited by 189
  13. 2019ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blockscited by 178
  14. 2022ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Modelscited by 141
  15. 2021OW-DETR: Open-world Detection Transformercited by 129
  16. 2020Incremental Few-Shot Object Detectioncited by 102
  17. 2021Class-agnostic Object Detection with Multi-modal Transformercited by 85
  18. 2022Representation Compensation Networks for Continual Semantic Segmentationcited by 72
  19. 2023Continual Detection Transformer for Incremental Object Detectioncited by 59
  20. 2020Incremental Object Detection via Meta-Learningcited by 58
  21. 2021Incremental Few-Shot Instance Segmentationcited by 49
  22. 2021RepMLPNet: Hierarchical Vision MLP with Re-parameterized Localitycited by 32
  23. 2019Relationship-Embedded Representation Learning for Grounding Referring Expressionscited by 25
  24. 2022Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detectioncited by 23
  25. 2022Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learningcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 5; 2026: 7.

15 papers.

Sort:

By area:

  1. 2025When Continue Learning Meets Multimodal Large Language Model: A Surveycited by 8
  2. 2024Towards Incremental Learning in Large Language Models: A Critical Reviewcited by 6
  3. 2024MR-GDINO: Efficient Open-World Continual Object Detectioncited by 5
  4. 2025DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detectioncited by 3
  5. 2025Realistic Evaluation of TabPFN v2 in Open Environmentscited by 3
  6. 2025iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object Detectioncited by 2
  7. 2025Mapping the Evolution of Research Contributions using KnoVocited by 2
  8. 2026EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformercited by 1
  9. 2026Robust Onion: Peeling Open Vocab Object Detectors Under Noisecited by 1
  10. 2024CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detectioncited by 0
  11. 2026ABRA: Teleporting Fine-Tuned Knowledge Across Domains for Open-Vocabulary Object Detectioncited by 0
  12. 2026Parameter-Efficient Semantic Augmentation for Enhancing Open-Vocabulary Object Detectioncited by 0
3 more
  1. 2026COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injectioncited by 0
  2. 2026C2Path: Class-Conditional Pathway Decoupling for Vision-Language Incremental Object Detectioncited by 0
  3. 2026MECAIL: Communication-Aware Incremental Learning for Object Detection with 14.6 KB Spatiotemporal Expertscited by 0