mlsanityData to 7 Oct 2026

Simple multi-dataset detection

arXiv 2102.13086 ↗First posted 25 Feb 2021cs.CVcited by 126

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

How do we build a general and broad object detection system? We use all labels of all concepts ever annotated. These labels span diverse datasets with potentially inconsistent taxonomies. In this paper, we present a simple method for training a unified detector on multiple large-scale datasets. We use dataset-specific training protocols and losses, but share a common detection architecture with dataset-specific outputs. We show how to automatically integrate these dataset-specific outputs into a common semantic taxonomy. In contrast to prior work, our approach does not require manual taxonomy reconciliation. Experiments show our learned taxonomy outperforms a expert-designed taxonomy in all datasets. Our multi-dataset detector performs as well as dataset-specific models on each training domain, and can generalize to new unseen dataset without fine-tuning on them. Code is available at https://github.com/xingyizhou/UniDet.

Key facts. Cited by 126 papers in the map (data through 7 Oct 2026). Builds on 30 of its 49 references that are in the map. First posted on arXiv 25 Feb 2021.

Builds on

30 of 49 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  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. 2017Mask R-CNNcited by 7,259
  5. 2017Squeeze-and-Excitation Networkscited by 4,763
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  8. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  9. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  10. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  11. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  12. 2020ResNeSt: Split-Attention Networkscited by 445
18 more
  1. 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 428
  2. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  3. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 283
  4. 2020VarifocalNet: An IoU-aware Dense Object Detectorcited by 230
  5. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  6. 2020Scaled-YOLOv4: Scaling Cross Stage Partial Networkcited by 211
  7. 2018Zero-Shot Object Detectioncited by 189
  8. 2017Playing for Benchmarkscited by 169
  9. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  10. 2019Hierarchical Deep Stereo Matching on High-resolution Imagescited by 126
  11. 2015Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networkscited by 115
  12. 2020Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detectioncited by 104
  13. 2019Towards Universal Object Detection by Domain Attentioncited by 89
  14. 2020Revisiting the Sibling Head in Object Detectorcited by 82
  15. 2020Object Detection with a Unified Label Space from Multiple Datasetscited by 65
  16. 2020Large-Scale Object Detection in the Wild from Imbalanced Multi-Labelscited by 35
  17. 2017Recent Advances in Zero-shot Recognitioncited by 28
  18. 2020Universal-RCNN: Universal Object Detector via Transferable Graph R-CNNcited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 18; 2023: 35; 2024: 32; 2025: 24; 2026: 11.

126 papers.

Sort:

By area:

  1. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  2. 2021Florence: A New Foundation Model for Computer Visioncited by 802
  3. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 613
  4. 2023T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generationcited by 253
  5. 2023LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Modelscited by 242
  6. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  7. 2022ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehensioncited by 119
  8. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 108
  9. 2024Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Wantcited by 98
  10. 2023HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Modelscited by 94
  11. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 85
  12. 2023Detecting Everything in the Open World: Towards Universal Object Detectioncited by 62
38 more
  1. 2024CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matchingcited by 60
  2. 2024UniTraj: A Unified Framework for Scalable Vehicle Trajectory Predictioncited by 51
  3. 2024VideoTetris: Towards Compositional Text-to-Video Generationcited by 51
  4. 2023TokenCompose: Text-to-Image Diffusion with Token-level Supervisioncited by 40
  5. 2023All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenescited by 40
  6. 2025Calibrated Multi-Preference Optimization for Aligning Diffusion Modelscited by 40
  7. 2023Uni3D: A Unified Baseline for Multi-dataset 3D Object Detectioncited by 39
  8. 2022DAMO-YOLO : A Report on Real-Time Object Detection Designcited by 38
  9. 2021INTERN: A New Learning Paradigm Towards General Visioncited by 33
  10. 2022BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-trainingcited by 33
  11. 2024Scalable Ranked Preference Optimization for Text-to-Image Generationcited by 33
  12. 2023DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Modelcited by 30
  13. 2023R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generationcited by 29
  14. 2023Prismer: A Vision-Language Model with Multi-Task Expertscited by 28
  15. 2022Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embeddingcited by 25
  16. 2024Multi-Space Alignments Towards Universal LiDAR Segmentationcited by 24
  17. 2024GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantationcited by 24
  18. 2023DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasetscited by 23
  19. 2024SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detectioncited by 22
  20. 2023Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipationcited by 21
  21. 2023LoCo: Locally Constrained Training-Free Layout-to-Image Synthesiscited by 21
  22. 2024UniDet3D: Multi-dataset Indoor 3D Object Detectioncited by 20
  23. 2023Cascade-DETR: Delving into High-Quality Universal Object Detectioncited by 19
  24. 2023FoodSAM: Any Food Segmentationcited by 19
  25. 2023SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentationcited by 19
  26. 2022Rethinking Few-Shot Object Detection on a Multi-Domain Benchmarkcited by 17
  27. 2023OmniLabel: A Challenging Benchmark for Language-Based Object Detectioncited by 16
  28. 2023ScaleDet: A Scalable Multi-Dataset Object Detectorcited by 16
  29. 2024GM-DF: Generalized Multi-Scenario Deepfake Detectioncited by 16
  30. 2023LMSeg: Language-guided Multi-dataset Segmentationcited by 15
  31. 2022Learning Semantic Segmentation from Multiple Datasets with Label Shiftscited by 14
  32. 2023MDT3D: Multi-Dataset Training for LiDAR 3D Object Detection Generalizationcited by 14
  33. 2023Long-tail Detection with Effective Class-Marginscited by 13
  34. 2023Unified Visual Relationship Detection with Vision and Language Modelscited by 13
  35. 2025Talk2Image: A Multi-Agent System for Multi-Turn Image Generation and Editingcited by 13
  36. 2022Learning to Discover and Detect Objectscited by 11
  37. 2024Scene Graph Disentanglement and Composition for Generalizable Complex Image Generationcited by 11
  38. 2024GT23D-Bench: A Comprehensive General Text-to-3D Generation Benchmarkcited by 11

50 most cited of 126 All 126 (JSON)