Track and Transfer: Watching Videos to Simulate Strong Human Supervision for Weakly-Supervised Object Detection
Open accessThe DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
The status quo approach to training object detectors requires expensive bounding box annotations. Our framework takes a markedly different direction: we transfer tracked object boxes from weakly-labeled videos to weakly-labeled images to automatically generate pseudo ground-truth boxes, which replace manually annotated bounding boxes. We first mine discriminative regions in the weakly-labeled image collection that frequently/rarely appear in the positive/ negative images. We then match those regions to videos and retrieve the corresponding tracked object boxes. Finally, we design a hough transform algorithm to vote for the best box to serve as the pseudo GT for each image, and use them to train an object detector. Together, these lead to state-of-the-art weakly-supervised detection results on the PASCAL 2007 and 2010 datasets.
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
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10578-9_23 · Cited by 3,034
Torralba, A., & Efros, A. A. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995347 · Cited by 2,440 · cited 1×
“However, such carefully labeled exemplars are expensive to obtain in the large numbers that are needed to fully represent a category’s variability, and methods trained in this manner can suffer from unintentional biases or errors imparted by annotators that hinder the system’s ability to generalize to new, unseen data…”
BackgroundUnsupervised Learning of Visual Representations Using Videos
Wang, X., & Gupta, A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.320 · Cited by 1,005
Ensemble of exemplar-SVMs for object detection and beyond
Malisiewicz, T., Gupta, A., & Efros, A. A. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126229 · Cited by 865
Cited by
Singh, K. K., & Lee, Y. J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.381 · Cited by 724
Self-citationMultiple Instance Detection Network with Online Instance Classifier Refinement
Tang, P., Wang, X., Bai, X., & Liu, W. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.326 · Cited by 496
LSTD: A Low-Shot Transfer Detector for Object Detection
Chen, H., Wang, Y., Wang, G., & Qiao, Y. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11716 · Cited by 370
Context-Aware Emotion Recognition Networks
Lee, J., Kim, S., Kim, S., Park, J., & Sohn, K. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01024 · Cited by 323
“…attention inference models [34, 35] have been investigated to identify discriminative regions where the networks attend, by mining discriminative regions [36], implicitly analyzing the higher-layer activation maps [34, 35], and designing different architecture of attention modules [37, 38].”
BackgroundWeakly Supervised Object Localization and Detection: A Survey
Zhang, D., Han, J., Cheng, G., & Yang, M.-H. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3074313 · Cited by 277
Zhang, D., Han, J., Zhao, L., & Meng, D. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-018-1112-4 · Cited by 164
“Then, we follow Kumar Singh et al. (2016) to treat the localized instances in the training images as the pseudo ground-truth to train the object detector, which is based on the fast R-CNN system (Girshick 2015).”
MethodInfluential
Metadata
- Authors
- Singh, K. K., Xiao, F., & Lee, Y. J.
- Venue
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2016-06
- Pages
- 3548-3556
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2338138401
- Cited by
- 63
- References
- 4
- FWCI
- 4.35
- 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.