Introduces the OACIR task requiring instance-level consistency via bounding-box anchors, a 160K real-world benchmark OACIRR, and the AdaFocal framework that adaptively focuses attention on the anchored region.
An open and com- prehensive pipeline for unified object grounding and detec- tion
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
abstract
Grounding-DINO is a state-of-the-art open-set detection model that tackles multiple vision tasks including Open-Vocabulary Detection (OVD), Phrase Grounding (PG), and Referring Expression Comprehension (REC). Its effectiveness has led to its widespread adoption as a mainstream architecture for various downstream applications. However, despite its significance, the original Grounding-DINO model lacks comprehensive public technical details due to the unavailability of its training code. To bridge this gap, we present MM-Grounding-DINO, an open-source, comprehensive, and user-friendly baseline, which is built with the MMDetection toolbox. It adopts abundant vision datasets for pre-training and various detection and grounding datasets for fine-tuning. We give a comprehensive analysis of each reported result and detailed settings for reproduction. The extensive experiments on the benchmarks mentioned demonstrate that our MM-Grounding-DINO-Tiny outperforms the Grounding-DINO-Tiny baseline. We release all our models to the research community. Codes and trained models are released at https://github.com/open-mmlab/mmdetection/tree/main/configs/mm_grounding_dino.
citation-role summary
baseline 2
method 2
citation-polarity summary
fields
cs.CV 12representative citing papers
A semi-supervised framework distills vision foundation models into compact instance segmentation experts that outperform their teachers by up to 11.9 AP on Cityscapes and 8.6 AP on ADE20K while being 11 times smaller.
UniRef-UAV defines multimodal universal referring for UAV scenes and shows a detection-style baseline with stronger no-target control than large MLLMs.
DroneFINE is a domain-aware PEFT approach for VLM-based drone detectors using foreground-aware multi-path adaptation and text-conditioned background suppression, outperforming standard PEFT and matching full fine-tuning on VisDrone and UAVDT with fewer trainable parameters.
Global prompt integration, visual-textual relation distillation and selective fusion make visual prompts discriminative enough for DETR-ViP to beat prior visual-prompt detectors by several mAP points.
PET-DINO unifies visual and text prompts in Grounding DINO via an alignment-friendly generation module and prompt-enriched training strategies to improve zero-shot open-set object detection.
Presents the first management-oriented multi-modal benchmark GovLA-10K and a vision-language reasoning framework GovLA-Reasoner with a spatially-aware adapter for low-altitude aerial perception.
DEViL offloads spatial grounding to a detector via a distilled reference-semantic token and temporal consistency regularization, reaching 43.1% m_vIoU at 14.33 FPS on HC-STVG.
Empirical study finds OV-OD robustness driven by vision backbone and image domain via layer-wise feature collapse analysis, validated with a low-parameter robustness improvement on real data.
DetRefiner fuses global and local features with a Transformer to refine OVOD confidence scores, delivering up to +10.1 AP gains on novel categories across multiple datasets.
VL-SAM-v3 retrieves visual prototypes from memory to generate sparse spatial and dense contextual priors that refine detection prompts, yielding gains on rare categories in LVIS for both open-vocabulary and open-ended settings.
The NTIRE 2026 CD-FSOD Challenge report details innovative methods and performance results from 19 teams on cross-domain few-shot object detection in open- and closed-source tracks.
citing papers explorer
-
Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval
Introduces the OACIR task requiring instance-level consistency via bounding-box anchors, a 160K real-world benchmark OACIRR, and the AdaFocal framework that adaptively focuses attention on the anchored region.
-
Training a Student Expert via Semi-Supervised Foundation Model Distillation
A semi-supervised framework distills vision foundation models into compact instance segmentation experts that outperform their teachers by up to 11.9 AP on Cityscapes and 8.6 AP on ADE20K while being 11 times smaller.
-
UniRef-UAV: A Multimodal Benchmark for Universal Referring in UAV Imagery
UniRef-UAV defines multimodal universal referring for UAV scenes and shows a detection-style baseline with stronger no-target control than large MLLMs.
-
DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images
DroneFINE is a domain-aware PEFT approach for VLM-based drone detectors using foreground-aware multi-path adaptation and text-conditioned background suppression, outperforming standard PEFT and matching full fine-tuning on VisDrone and UAVDT with fewer trainable parameters.
-
DETR-ViP: Detection Transformer with Robust Discriminative Visual Prompts
Global prompt integration, visual-textual relation distillation and selective fusion make visual prompts discriminative enough for DETR-ViP to beat prior visual-prompt detectors by several mAP points.
-
PET-DINO: Unifying Visual Cues into Grounding DINO with Prompt-Enriched Training
PET-DINO unifies visual and text prompts in Grounding DINO via an alignment-friendly generation module and prompt-enriched training strategies to improve zero-shot open-set object detection.
-
Focus on What Really Matters in Low-Altitude Governance: A Management-Centric Multi-Modal Benchmark with Implicitly Coordinated Vision-Language Reasoning Framework
Presents the first management-oriented multi-modal benchmark GovLA-10K and a vision-language reasoning framework GovLA-Reasoner with a spatially-aware adapter for low-altitude aerial perception.
-
Detector-Empowered Video Large Language Model for Efficient Spatio-Temporal Grounding
DEViL offloads spatial grounding to a detector via a distilled reference-semantic token and temporal consistency regularization, reaching 43.1% m_vIoU at 14.33 FPS on HC-STVG.
-
Robust Onion: Peeling Open Vocab Object Detectors Under Noise
Empirical study finds OV-OD robustness driven by vision backbone and image domain via layer-wise feature collapse analysis, validated with a low-parameter robustness improvement on real data.
-
DetRefiner: Model-Agnostic Detection Refinement with Feature Fusion Transformer
DetRefiner fuses global and local features with a Transformer to refine OVOD confidence scores, delivering up to +10.1 AP gains on novel categories across multiple datasets.
-
VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection
VL-SAM-v3 retrieves visual prototypes from memory to generate sparse spatial and dense contextual priors that refine detection prompts, yielding gains on rare categories in LVIS for both open-vocabulary and open-ended settings.
-
The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results
The NTIRE 2026 CD-FSOD Challenge report details innovative methods and performance results from 19 teams on cross-domain few-shot object detection in open- and closed-source tracks.