IAdet: Simplest human-in-the-loop object detection
Not on the map. Why?
Abstract (arXiv)
This work proposes a strategy for training models while annotating data named Intelligent Annotation (IA). IA involves three modules: (1) assisted data annotation, (2) background model training, and (3) active selection of the next datapoints. Under this framework, we open-source the IAdet tool, which is specific for single-class object detection. Additionally, we devise a method for automatically evaluating such a human-in-the-loop system. For the PASCAL VOC dataset, the IAdet tool reduces the database annotation time by 25% while providing a trained model for free. These results are obtained for a deliberately very simple IAdet design. As a consequence, IAdet is susceptible to multiple easy improvements, paving the way for powerful human-in-the-loop object detection systems.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 38 of its 50 references that are in the map. First posted on arXiv 4 Jul 2023.
Builds on
38 of 50 references.
References · 38
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2020End-to-End Object Detection with Transformerscited by 7,384
- 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
- 2016Feature Pyramid Networks for Object Detectioncited by 5,021
- 2015SSD: Single Shot MultiBox Detectorcited by 3,125
- 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
- 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
- 2018Deep Visual Domain Adaptation: A Surveycited by 634
26 more
- 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
- 2020A Survey of Deep Active Learningcited by 547
- 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
- 2021Urban Radiance Fieldscited by 263
- 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 242
- 2019The VIA Annotation Software for Images, Audio and Videocited by 166
- 2021VOLO: Vision Outlooker for Visual Recognitioncited by 164
- 2021Reviving Iterative Training with Mask Guidance for Interactive Segmentationcited by 162
- 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
- 2019Large-scale interactive object segmentation with human annotatorscited by 109
- 2022FocalClick: Towards Practical Interactive Image Segmentationcited by 101
- 2022Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillationcited by 93
- 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
- 2021Self-Supervised Pretraining Improves Self-Supervised Pretrainingcited by 81
- 2021Multiple instance active learning for object detectioncited by 77
- 2021DETReg: Unsupervised Pretraining with Region Priors for Object Detectioncited by 76
- 2021Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Typescited by 54
- 2020Towards Robust and Reproducible Active Learning Using Neural Networkscited by 53
- 2022Entropy-based Active Learning for Object Detection with Progressive Diversity Constraintcited by 53
- 2019Parting with Illusions about Deep Active Learningcited by 38
- 2021A Survey of Self-Supervised and Few-Shot Object Detectioncited by 35
- 2021Transferability Metrics for Selecting Source Model Ensemblescited by 24
- 2020Transfer Learning or Self-supervised Learning? A Tale of Two Pretraining Paradigmscited by 23
- 2020Iterative Bounding Box Annotation for Object Detectioncited by 15
- 2022Interactive Multi-Class Tiny-Object Detectioncited by 14
- 2021Generalizing Interactive Backpropagating Refinement for Dense Predictioncited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.