mlsanityData to 7 Oct 2026

Towards Domain-Generalized Open-Vocabulary Object Detection: A Progressive Domain-invariant Cross-modal Alignment Method

arXiv 2603.27556 ↗First posted 29 Mar 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Open-Vocabulary Object Detection (OVOD) has achieved remarkable success in generalizing to novel categories. However, this success often rests on the implicit assumption of domain stationarity. In this work, we revisit the OVOD paradigm and study a key vulnerability: the fragile coupling between visual manifolds and textual embeddings under distribution shifts. We first formulate Domain-Generalized Open-Vocabulary Object Detection (DG-OVOD) as an evaluation protocol for open-vocabulary recognition under visual shifts. Through empirical analysis, we observe that visual shifts can destabilize the latent cross-modal space, causing novel-category visual signals to drift away from their semantic anchors. Motivated by these observations, we propose Progressive Domain-invariant Cross-modal Alignment (PICA). PICA departs from uniform training by introducing a multi-level curriculum based on ambiguity and signal strength. It constructs a quality-adjusted curriculum over pseudo-word prototypes, refined by sample reliability and visual consistency, to encourage more stable cross-domain modality alignment. Our findings suggest that OVOD robustness under domain shifts is closely linked to the stability of the latent cross-modal alignment space. Our work provides a DG-OVOD evaluation protocol and a practical perspective on building more generalizable open-vocabulary systems beyond static laboratory conditions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 52 of its 74 references that are in the map. First posted on arXiv 29 Mar 2026.

Builds on

52 of 74 references.

References · 52

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  6. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  7. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  8. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  9. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,352
  10. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,337
  11. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,224
  12. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
38 more
  1. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  2. 2021Grounded Language-Image Pre-trainingcited by 1,147
  3. 2016Modeling Context in Referring Expressionscited by 1,054
  4. 2020In Search of Lost Domain Generalizationcited by 1,042
  5. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  6. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  7. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  8. 2021SimVLM: Simple Visual Language Model Pretraining with Weak Supervisioncited by 645
  9. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 613
  10. 2021RegionCLIP: Region-based Language-Image Pretrainingcited by 612
  11. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  12. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 498
  13. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 441
  14. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  15. 2020Open-Vocabulary Object Detection Using Captionscited by 427
  16. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 350
  17. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
  18. 2017Automated Curriculum Learning for Neural Networkscited by 251
  19. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  20. 2018Progressive Feature Alignment for Unsupervised Domain Adaptationcited by 183
  21. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 163
  22. 2019Learning to Optimize Domain Specific Normalization for Domain Generalizationcited by 160
  23. 2022Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detectioncited by 145
  24. 2023CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matchingcited by 133
  25. 2023Aligning Bag of Regions for Open-Vocabulary Object Detectioncited by 119
  26. 2017Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenescited by 105
  27. 2022Exploiting Unlabeled Data with Vision and Language Models for Object Detectioncited by 97
  28. 2018Curriculum Adversarial Trainingcited by 89
  29. 2025Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspectivecited by 55
  30. 2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptationcited by 49
  31. 2023COCO-O: A Benchmark for Object Detectors under Natural Distribution Shiftscited by 34
  32. 2023Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Modelscited by 30
  33. 2023LP-OVOD: Open-Vocabulary Object Detection by Linear Probingcited by 29
  34. 2024OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervisioncited by 22
  35. 2024Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalizationcited by 20
  36. 2024Retrieval-Augmented Open-Vocabulary Object Detectioncited by 20
  37. 2022Curriculum Learning for Data-Efficient Vision-Language Alignmentcited by 11
  38. 2024Cross-domain Multi-modal Few-shot Object Detection via Rich Textcited by 5

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.