Training Object Class Detectors with Click Supervision
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Training object class detectors typically requires a large set of images with objects annotated by bounding boxes. However, manually drawing bounding boxes is very time consuming. In this paper we greatly reduce annotation time by proposing center-click annotations: we ask annotators to click on the center of an imaginary bounding box which tightly encloses the object instance. We then incorporate these clicks into existing Multiple Instance Learning techniques for weakly supervised object localization, to jointly localize object bounding boxes over all training images. Extensive experiments on PASCAL VOC 2007 and MS COCO show that: (1) our scheme delivers high-quality detectors, performing substantially better than those produced by weakly supervised techniques, with a modest extra annotation effort, (2) these detectors in fact perform in a range close to those trained from manually drawn bounding boxes, (3) as the center-click task is very fast, our scheme reduces total annotation time by 9x to 18x.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Selective Search for Object Recognition
Uijlings, J. R. R., van de Sande, K. E. A., Gevers, T., & Smeulders, A. W. M. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0620-5 · Cited by 5,980
Self-citationLabelMe: A Database and Web-Based Tool for Image Annotation
Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-007-0090-8 · Cited by 4,210
Solving the multiple instance problem with axis-parallel rectangles
Dietterich, T. G., Lathrop, R. H., & Lozano-Pérez, T. (1997) · Artificial Intelligence · doi:10.1016/s0004-3702(96)00034-3 · Cited by 2,866 · cited 1×
“WSOL is often addressed as a Multiple Instance Learning (MIL) problem [6, 10, 13, 14, 59, 61, 62, 63].”
BackgroundEdge Boxes: Locating Object Proposals from Edges
Zitnick, C. L., & Dollár, P. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_26 · Cited by 2,656
Fei-Fei, L., Fergus, R., & Perona, P. (2007) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2005.09.012 · Cited by 2,359
Learning to detect unseen object classes by between-class attribute transfer
Lampert, C. H., Nickisch, H., & Harmeling, S. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206594 · Cited by 1,849 · cited 1×
“An alternative direction is transfer learning, where an appearance model for a new class is learned from bounding box annotations on examples of related classes [3, 18, 21, 22, 35, 37, 50].”
BackgroundExecutive control of cognitive processes in task switching
Rubinstein, J. S., Meyer, D. E., & Evans, J. E. (2001) · Journal of Experimental Psychology: Human Perception and Performance · doi:10.1037//0096-1523.27.4.763 · Cited by 1,207 · cited 1×
“More generally, it avoids taskswitching which is well-known to increase response time and decrease accuracy [51].”
BackgroundTomasello, M., Carpenter, M., & Liszkowski, U. (2007) · Child Development · doi:10.1111/j.1467-8624.2007.01025.x · Cited by 1,039
Material recognition in the wild with the Materials in Context Database
Bell, S., Upchurch, P., Snavely, N., & Bala, K. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298970 · Cited by 516
LSDA: Large Scale Detection Through Adaptation
Hoffman, J., Guadarrama, S., Tzeng, E., Hu, R., Donahue, J., Girshick, R., Darrell, T., & Saenko, K. (2014) · arXiv · doi:10.48550/arxiv.1407.5035 · Cited by 284 · cited 1×
“An alternative direction is transfer learning, where an appearance model for a new class is learned from bounding box annotations on examples of related classes [3, 18, 21, 22, 35, 37, 50].”
Background
Cited by
Object Detection With Deep Learning: A Review
Zhao, Z.-Q., Zheng, P., Xu, S.-T., & Wu, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2876865 · Cited by 5,545
Deep Extreme Cut: From Extreme Points to Object Segmentation
Maninis, K.-K., Caelles, S., Pont-Tuset, J., & Van Gool, L. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00071 · Cited by 450
Kellenberger, B., Marcos, D., & Tuia, D. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00182 · Cited by 33
QBox: Partial Transfer Learning With Active Querying for Object Detection
Tang, Y.-P., Wei, X.-S., Zhao, B., & Huang, S.-J. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3111621 · Cited by 17
Weakly- and Semi-Supervised Fast Region-Based CNN for Object Detection
Wang, X.-G., Wang, J.-S., Tang, P., & Liu, W.-Y. (2019) · Journal of Computer Science and Technology · doi:10.1007/s11390-019-1975-z · Cited by 8
Metadata
- Authors
- Papadopoulos, D. P., Uijlings, J. R. R., Keller, F., & Ferrari, V.
- Venue
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2017-07
- Pages
- 180-189
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2608567823
- Cited by
- 113
- References
- 11
- FWCI
- 3.32
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.