mlsanityData to 14 Oct 2026

Semi-Supervised Domain Generalization for Object Detection via Language-Guided Feature Alignment

arXiv 2309.13525 ↗First posted 24 Sep 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Existing domain adaptation (DA) and generalization (DG) methods in object detection enforce feature alignment in the visual space but face challenges like object appearance variability and scene complexity, which make it difficult to distinguish between objects and achieve accurate detection. In this paper, we are the first to address the problem of semi-supervised domain generalization by exploring vision-language pre-training and enforcing feature alignment through the language space. We employ a novel Cross-Domain Descriptive Multi-Scale Learning (CDDMSL) aiming to maximize the agreement between descriptions of an image presented with different domain-specific characteristics in the embedding space. CDDMSL significantly outperforms existing methods, achieving 11.7% and 7.5% improvement in DG and DA settings, respectively. Comprehensive analysis and ablation studies confirm the effectiveness of our method, positioning CDDMSL as a promising approach for domain generalization in object detection tasks.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 49 of its 60 references that are in the map. First posted on arXiv 24 Sep 2023.

Builds on

49 of 60 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2017Mask R-CNNcited by 7,277
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  8. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
  9. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,462
  10. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  11. 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,214
  12. 2021Grounded Language-Image Pre-trainingcited by 1,156
37 more
  1. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 906
  2. 2021RegionCLIP: Region-based Language-Image Pretrainingcited by 616
  3. 2021Domain Generalization with MixStylecited by 566
  4. 2021ClipCap: CLIP Prefix for Image Captioningcited by 559
  5. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  6. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 464
  7. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 443
  8. 2020Open-Vocabulary Object Detection Using Captionscited by 427
  9. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 376
  10. 2020VirTex: Learning Visual Representations from Textual Annotationscited by 339
  11. 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 270
  12. 2018Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptationcited by 218
  13. 2018Zero-Shot Object Detectioncited by 189
  14. 2020Unbiased Mean Teacher for Cross-domain Object Detectioncited by 159
  15. 2019Exploring Object Relation in Mean Teacher for Cross-Domain Detectioncited by 137
  16. 2020Harmonizing Transferability and Discriminability for Adapting Object Detectorscited by 126
  17. 2021Cross-Domain Adaptive Teacher for Object Detectioncited by 126
  18. 2019Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detectioncited by 123
  19. 2021Open Domain Generalization with Domain-Augmented Meta-Learningcited by 115
  20. 2020Cross-domain Detection via Graph-induced Prototype Alignmentcited by 109
  21. 2022Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbonecited by 109
  22. 2020Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detectorcited by 107
  23. 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
  24. 2020Cross-domain Object Detection through Coarse-to-Fine Feature Adaptationcited by 82
  25. 2019Automatic adaptation of object detectors to new domains using self-trainingcited by 66
  26. 2022Instance Relation Graph Guided Source-Free Domain Adaptive Object Detectioncited by 55
  27. 2019Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignmentcited by 51
  28. 2021Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformerscited by 49
  29. 2022Cross Domain Object Detection by Target-Perceived Dual Branch Distillationcited by 46
  30. 2019Domain Adaptation for Object Detection via Style Consistencycited by 45
  31. 2021Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detectioncited by 45
  32. 2021Semi-Supervised Domain Generalization with Stochastic StyleMatchcited by 43
  33. 2021Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentationcited by 36
  34. 2019Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detectioncited by 31
  35. 2021Domain-Specific Suppression for Adaptive Object Detectioncited by 26
  36. 2021AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detectioncited by 19
  37. 2017Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Taskscited by 9

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Seeking Flat Minima with Mean Teacher on Semi- and Weakly-Supervised Domain Generalization for Object Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning
  2. 2025Boosting Single-domain Generalized Object Detection via Vision-Language Knowledge Interaction
  3. 2023CLIP the Gap: A Single Domain Generalization Approach for Object Detection
  4. 2026SemAlign: Language Guided Semi-supervised Domain Generalization
  5. 2026CD-FKD: Cross-Domain Feature Knowledge Distillation for Robust Single-Domain Generalization in Object Detection
  6. 2025Language-Driven Dual Style Mixing for Single-Domain Generalized Object Detection
  7. 2024Feature Based Methods in Domain Adaptation for Object Detection: A Review Paper
  8. 2024PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization