2000 character limit reached
IAdet: Simplest human-in-the-loop object detection (2307.01582v1)
Published 4 Jul 2023 in cs.CV, cs.AI, cs.HC, and cs.LG
Abstract: 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.
- “Iterative Bounding Box Annotation for Object Detection” In 2020 25th International Conference on Pattern Recognition (ICPR), 2021, pp. 4040–4046
- “Transferability Metrics for Selecting Source Model Ensembles” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7936–7946
- “Gone fishing: Neural active learning with fisher embeddings” In Advances in Neural Information Processing Systems 34, 2021, pp. 8927–8939
- “Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds” In CoRR abs/1906.03671, 2019 arXiv:1906.03671
- “DETReg: Unsupervised Pretraining With Region Priors for Object Detection” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 14605–14615
- Adrien Bardes, Jean Ponce and Yann LeCun “Vicreg: Variance-invariance-covariance regularization for self-supervised learning” In arXiv preprint arXiv:2105.04906, 2021
- “The power of ensembles for active learning in image classification” In Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 9368–9377
- Rodrigo Benenson, Stefan Popov and Vittorio Ferrari “Large-scale interactive object segmentation with human annotators” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 11700–11709
- “Language models are few-shot learners” In Advances in neural information processing systems 33, 2020, pp. 1877–1901
- “End-to-end object detection with transformers” In European conference on computer vision, 2020, pp. 213–229 Springer
- “MMDetection: Open MMLab Detection Toolbox and Benchmark” In arXiv preprint arXiv:1906.07155, 2019
- “FocalClick: Towards Practical Interactive Image Segmentation” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 1300–1309
- “Phraseclick: toward achieving flexible interactive segmentation by phrase and click” In European Conference on Computer Vision, 2020, pp. 417–435 Springer
- Shi Dong, Ping Wang and Khushnood Abbas “A survey on deep learning and its applications” In Computer Science Review 40 Elsevier, 2021, pp. 100379
- “An image is worth 16x16 words: Transformers for image recognition at scale” In arXiv preprint arXiv:2010.11929, 2020
- “The VIA Annotation Software for Images, Audio and Video” In Proceedings of the 27th ACM International Conference on Multimedia, MM ’19 Nice, France: ACM, 2019 DOI: 10.1145/3343031.3350535
- “The Pascal Visual Object Classes (VOC) Challenge” In International Journal of Computer Vision 88.2, 2010, pp. 303–338
- Eshan Gaur, Vikas Saxena and Sandeep K Singh “Video annotation tools: A Review” In 2018 International Conference on Advances in Computing, Communication Control and Networking (ICACCCN), 2018, pp. 911–914 IEEE
- “Deep residual learning for image recognition” In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778
- “Masked autoencoders are scalable vision learners” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16000–16009
- “Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9068–9077
- “A survey of self-supervised and few-shot object detection” In IEEE Transactions on Pattern Analysis and Machine Intelligence IEEE, 2022
- Benjamin Kellenberger, Devis Tuia and Dan Morris “AIDE: Accelerating image-based ecological surveys with interactive machine learning” In Methods in Ecology and Evolution 11.12, 2020, pp. 1716–1727 DOI: 10.1111/2041-210X.13489
- Mona Köhler, Markus Eisenbach and Horst-Michael Gross “Few-Shot Object Detection: A Survey” In arXiv preprint arXiv:2112.11699, 2021
- “Interactive Multi-Class Tiny-Object Detection” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 14136–14145
- Fanqing Lin, Brian Price and Tony Martinez “Generalizing Interactive Backpropagating Refinement for Dense Prediction Networks” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 773–782
- “Feature pyramid networks for object detection” In Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 2117–2125
- “Microsoft coco: Common objects in context” In European conference on computer vision, 2014, pp. 740–755 Springer
- “Ssd: Single shot multibox detector” In European conference on computer vision, 2016, pp. 21–37 Springer
- “Online continual learning in image classification: An empirical survey” In Neurocomputing 469 Elsevier, 2022, pp. 28–51
- “Factors of influence for transfer learning across diverse appearance domains and task types” In arXiv preprint arXiv:2103.13318, 2021
- “Parting with Illusions about Deep Active Learning” In arXiv preprint arXiv:1912.05361, 2019 DOI: 10.48550/ARXIV.1912.05361
- “Towards robust and reproducible active learning using neural networks” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 223–232
- “Self-supervised pretraining improves self-supervised pretraining” In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 2584–2594
- “Urban radiance fields” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 12932–12942
- “A survey of deep active learning” In ACM computing surveys (CSUR) 54.9 ACM New York, NY, 2021, pp. 1–40
- “Faster r-cnn: Towards real-time object detection with region proposal networks” In Advances in neural information processing systems 28, 2015
- “High-resolution image synthesis with latent diffusion models” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10684–10695
- “LabelMe: a database and web-based tool for image annotation” In International journal of computer vision 77.1 Springer, 2008, pp. 157–173
- “Active learning for convolutional neural networks: A core-set approach” In arXiv preprint arXiv:1708.00489, 2017
- Burr Settles “Active learning literature survey”, 2009
- Konstantin Sofiiuk, Ilya A Petrov and Anton Konushin “Reviving iterative training with mask guidance for interactive segmentation” In 2022 IEEE International Conference on Image Processing (ICIP), 2022, pp. 3141–3145 IEEE
- Jesper E Van Engelen and Holger H Hoos “A survey on semi-supervised learning” In Machine Learning 109.2 Springer, 2020, pp. 373–440
- “Deep visual domain adaptation: A survey” In Neurocomputing 312 Elsevier, 2018, pp. 135–153
- “Frustratingly simple few-shot object detection” In arXiv preprint arXiv:2003.06957, 2020
- “Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation” In arXiv preprint arXiv:2205.14141, 2022
- Jiaxi Wu, Jiaxin Chen and Di Huang “Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9397–9406
- “Transfer learning or self-supervised learning? A tale of two pretraining paradigms” In arXiv preprint arXiv:2007.04234, 2020
- “Volo: Vision outlooker for visual recognition” In IEEE Transactions on Pattern Analysis and Machine Intelligence IEEE, 2022
- “Multiple instance active learning for object detection” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 5330–5339
Sponsored by Paperpile, the PDF & BibTeX manager trusted by top AI labs.
Get 30 days freePaper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.