Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation
Not on the map. Why?
Abstract (arXiv)
Can we detect common objects in a variety of image domains without instance-level annotations? In this paper, we present a framework for a novel task, cross-domain weakly supervised object detection, which addresses this question. For this paper, we have access to images with instance-level annotations in a source domain (e.g., natural image) and images with image-level annotations in a target domain (e.g., watercolor). In addition, the classes to be detected in the target domain are all or a subset of those in the source domain. Starting from a fully supervised object detector, which is pre-trained on the source domain, we propose a two-step progressive domain adaptation technique by fine-tuning the detector on two types of artificially and automatically generated samples. We test our methods on our newly collected datasets containing three image domains, and achieve an improvement of approximately 5 to 20 percentage points in terms of mean average precision (mAP) compared to the best-performing baselines.
Key facts. Cited by 218 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Mar 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 40; 2022: 36; 2023: 44; 2024: 42; 2025: 34; 2026: 22.
218 papers.
Sort:
By area:
- 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 186
- 2021Cross-Domain Adaptive Teacher for Object Detectioncited by 125
- 2022Exploiting Unlabeled Data with Vision and Language Models for Object Detectioncited by 97
- 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
- 2022High-Quality Entity Segmentationcited by 93
- 2023CLIP the Gap: A Single Domain Generalization Approach for Object Detectioncited by 87
- 2021Class-agnostic Object Detection with Multi-modal Transformercited by 85
- 2022Self-Training: A Surveycited by 85
- 2022A Closer Look at Smoothness in Domain Adversarial Trainingcited by 85
- 2021Weakly Supervised Object Localization and Detection: A Surveycited by 84
- 2022SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detectioncited by 74
- 2023Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenescited by 68
38 more
- 2021Uncertainty-Aware Unsupervised Domain Adaptation in Object Detectioncited by 59
- 2022Instance Relation Graph Guided Source-Free Domain Adaptive Object Detectioncited by 55
- 2021MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptationcited by 54
- 2023Contrastive Mean Teacher for Domain Adaptive Object Detectorscited by 52
- 2021Vector-Decomposed Disentanglement for Domain-Invariant Object Detectioncited by 47
- 2024Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detectorcited by 43
- 2023Text-image Alignment for Diffusion-based Perceptioncited by 42
- 2021Spectral Unsupervised Domain Adaptation for Visual Recognitioncited by 40
- 2021Decoupled Adaptation for Cross-Domain Object Detectioncited by 37
- 2022Task-specific Inconsistency Alignment for Domain Adaptive Object Detectioncited by 37
- 2021Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularizationcited by 36
- 2022Towards Online Domain Adaptive Object Detectioncited by 36
- 2023COCO-O: A Benchmark for Object Detectors under Natural Distribution Shiftscited by 34
- 2022Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptationcited by 33
- 2024AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Modelscited by 29
- 2024Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignmentcited by 29
- 2021HLA-Face: Joint High-Low Adaptation for Low Light Face Detectioncited by 28
- 2022InstaFormer: Instance-Aware Image-to-Image Translation with Transformercited by 28
- 2022Multi-Granularity Alignment Domain Adaptation for Object Detectioncited by 28
- 2021I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectorscited by 27
- 2021GAIA: A Transfer Learning System of Object Detection that Fits Your Needscited by 27
- 2021SimROD: A Simple Adaptation Method for Robust Object Detectioncited by 27
- 2021Domain-Specific Suppression for Adaptive Object Detectioncited by 26
- 2022Gradual Domain Adaptation without Indexed Intermediate Domainscited by 26
- 2022Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embeddingcited by 25
- 2023Adversarial Alignment for Source Free Object Detectioncited by 25
- 2021DA-DETR: Domain Adaptive Detection Transformer with Information Fusioncited by 24
- 2021Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detectioncited by 24
- 2025Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detectioncited by 24
- 2023DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detectioncited by 23
- 2023DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasetscited by 23
- 2021Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detectioncited by 21
- 2021Memory-guided Unsupervised Image-to-image Translationcited by 21
- 2023Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detectioncited by 21
- 2022Towards Robust Adaptive Object Detection under Noisy Annotationscited by 20
- 2024The Manga Whisperer: Automatically Generating Transcriptions for Comicscited by 20
- 2021AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detectioncited by 19
- 2022SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object Detectioncited by 19
50 most cited of 218 All 218 (JSON)
- 2026DESA-TTA: Dynamic EMA and Source Anchoring for Test-Time Adaptation1 Sep 2026
- 2026PISA: A Pseudo-Individual Source-Domain Feature Adaptation Framework for Test-Time Open-Vocabulary Object Detection14 Aug 2026
- 2026Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detection2 Aug 2026
- 2026Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection19 Jul 2026
- 2026Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection8 Jul 2026
- 2026Assessing Distribution Shift in Human Activity Recognition for Domain Generalization23 Jun 2026
- 2026Multi-Modal Guided Multi-Source Domain Adaptation for Object Detection13 May 2026
- 2026MUSDA: Multi-source Multi-modality Unsupervised Domain Adaptive 3D Object Detection for Autonomous Driving11 May 2026
- 2026Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning10 May 2026
- 2026Bridge: Basis-Driven Causal Inference Marries VFMs for Domain Generalization29 Apr 2026
- 2026Multi-Domain Learning with Global Expert Mapping20 Apr 2026
- 2026BEM: Training-Free Background Embedding Memory for False-Positive Suppression in Real-Time Fixed-Background Camera13 Apr 2026
38 more
- 2026Towards Adaptive Open-Set Object Detection via Category-Level Collaboration Knowledge Mining13 Apr 2026
- 2026Generalization Under Scrutiny: Cross-Domain Detection Progresses, Pitfalls, and Persistent Challenges9 Apr 2026
- 2026Language-Pretraining-Induced Bias: A Strong Foundation for General Vision Tasks2 Apr 2026
- 2026DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object Detection19 Mar 2026
- 2026Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection19 Mar 2026
- 2026Prompt-Free Universal Region Proposal Network18 Mar 2026
- 2026EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer24 Feb 2026
- 2026Learning Multi-Modal Prototypes for Cross-Domain Few-Shot Object Detection21 Feb 2026
- 2026Bridging Day and Night: Target-Class Hallucination Suppression in Unpaired Image Translation17 Feb 2026
- 2026LAB-Det: Language as a Domain-Invariant Bridge for Training-Free One-Shot Domain Generalization in Object Detection6 Feb 2026
- 2025Exploring Syn-to-Real Domain Adaptation for Military Target Detection29 Dec 2025
- 2025Foundation Model Priors Enhance Object Focus in Feature Space for Source-Free Object Detection19 Dec 2025
- 2025Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection16 Nov 2025
- 2025GALA: A GlobAl-LocAl Approach for Multi-Source Active Domain Adaptation25 Oct 2025
- 2025VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors1 Oct 2025
- 2025Benchmarking Vision-Language and Multimodal Large Language Models in Zero-shot and Few-shot Scenarios: A study on Christian Iconography23 Sep 2025
- 2025RICO: Two Realistic Benchmarks and an In-Depth Analysis for Incremental Learning in Object Detection19 Aug 2025
- 2025ODOV: Benchmark the Open-Domain Open-Vocabulary Object Detection2 Aug 2025
- 2025Adapting Vehicle Detectors for Aerial Imagery to Unseen Domains with Weak Supervision28 Jul 2025
- 2025De-Simplifying Pseudo Labels to Enhancing Domain Adaptive Object Detection1 Jul 2025
- 2025Embodied Domain Adaptation for Object Detection27 Jun 2025
- 2025TITAN: Query-Token based Domain Adaptive Adversarial Learning26 Jun 2025
- 2025DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic26 Jun 2025
- 2025Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability26 Jun 2025
- 2025Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection6 Jun 2025
- 2025Diffusion Domain Teacher: Diffusion Guided Domain Adaptive Object Detector4 Jun 2025
- 2025Domain Adaptation for Multi-label Image Classification: a Discriminator-free Approach20 May 2025
- 2025Language-Driven Dual Style Mixing for Single-Domain Generalized Object Detection12 May 2025
- 2025CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion2 May 2025
- 2025DG-DETR: Toward Domain Generalized Detection Transformer28 Apr 2025
- 2025SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systems22 Apr 2025
- 2025Context Aware Grounded Teacher for Source Free Object Detection21 Apr 2025
- 2025COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts14 Apr 2025
- 2025Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation13 Apr 2025
- 2025Visually Similar Pair Alignment for Robust Cross-Domain Object Detection9 Apr 2025
- 2025Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection6 Apr 2025
- 2025From Panels to Prose: Generating Literary Narratives from Comics30 Mar 2025
- 2025Bezier Splatting for Fast and Differentiable Vector Graphics Rendering20 Mar 2025
50 newest of 218 All 218 (JSON)
- 2023Text-image Alignment for Diffusion-based Perceptioncited by 42
- 2023DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detectioncited by 23
- 2024TALE: Training-free Cross-domain Image Composition via Adaptive Latent Manipulation and Energy-guided Optimizationcited by 9
- 2025Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detectioncited by 6
- 2024AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Taskscited by 4
- 2025Diffusion Domain Teacher: Diffusion Guided Domain Adaptive Object Detectorcited by 4
- 2024No Annotations for Object Detection in Art through Stable Diffusioncited by 2
- 2025Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferabilitycited by 2
- 2025Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability26 Jun 2025
- 2025Diffusion Domain Teacher: Diffusion Guided Domain Adaptive Object Detector4 Jun 2025
- 2025Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection3 Mar 2025
- 2024No Annotations for Object Detection in Art through Stable Diffusion9 Dec 2024
- 2024AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Tasks24 Nov 2024
- 2024TALE: Training-free Cross-domain Image Composition via Adaptive Latent Manipulation and Energy-guided Optimization7 Aug 2024
- 2023Text-image Alignment for Diffusion-based Perception29 Sep 2023
- 2023DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detection7 Sep 2023
- 2025Vision-Language Model for Object Detection and Segmentation: A Review and Evaluationcited by 10
- 2024One missing piece in Vision and Language: A Survey on Comics Understandingcited by 8
- 2025From Panels to Prose: Generating Literary Narratives from Comicscited by 5
- 2025Benchmarking Vision-Language and Multimodal Large Language Models in Zero-shot and Few-shot Scenarios: A study on Christian Iconographycited by 2
- 2025COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shiftscited by 1
- 2025Benchmarking Vision-Language and Multimodal Large Language Models in Zero-shot and Few-shot Scenarios: A study on Christian Iconography23 Sep 2025
- 2025COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts14 Apr 2025
- 2025Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation13 Apr 2025
- 2025From Panels to Prose: Generating Literary Narratives from Comics30 Mar 2025
- 2024One missing piece in Vision and Language: A Survey on Comics Understanding14 Sep 2024
- 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 186
- 2021Cross-Domain Adaptive Teacher for Object Detectioncited by 125
- 2022Exploiting Unlabeled Data with Vision and Language Models for Object Detectioncited by 97
- 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
- 2022High-Quality Entity Segmentationcited by 93
- 2023CLIP the Gap: A Single Domain Generalization Approach for Object Detectioncited by 87
- 2021Class-agnostic Object Detection with Multi-modal Transformercited by 85
- 2022Self-Training: A Surveycited by 85
- 2022A Closer Look at Smoothness in Domain Adversarial Trainingcited by 85
- 2021Weakly Supervised Object Localization and Detection: A Surveycited by 84
- 2022SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detectioncited by 74
- 2023Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenescited by 68
12 most cited of 198 All 198 (JSON)
- 2026DESA-TTA: Dynamic EMA and Source Anchoring for Test-Time Adaptation1 Sep 2026
- 2026PISA: A Pseudo-Individual Source-Domain Feature Adaptation Framework for Test-Time Open-Vocabulary Object Detection14 Aug 2026
- 2026Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detection2 Aug 2026
- 2026Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection19 Jul 2026
- 2026Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection8 Jul 2026
- 2026Assessing Distribution Shift in Human Activity Recognition for Domain Generalization23 Jun 2026
- 2026Multi-Modal Guided Multi-Source Domain Adaptation for Object Detection13 May 2026
- 2026MUSDA: Multi-source Multi-modality Unsupervised Domain Adaptive 3D Object Detection for Autonomous Driving11 May 2026
- 2026Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning10 May 2026
- 2026Bridge: Basis-Driven Causal Inference Marries VFMs for Domain Generalization29 Apr 2026
- 2026BEM: Training-Free Background Embedding Memory for False-Positive Suppression in Real-Time Fixed-Background Camera13 Apr 2026
- 2026Towards Adaptive Open-Set Object Detection via Category-Level Collaboration Knowledge Mining13 Apr 2026
12 newest of 198 All 198 (JSON)