Weakly supervised discriminative localization and classification: a joint learning process
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Visual categorization problems, such as object classification or action recognition, are increasingly often approached using a detection strategy: a classifier function is first applied to candidate subwindows of the image or the video, and then the maximum classifier score is used for class decision. Traditionally, the subwindow classifiers are trained on a large collection of examples manually annotated with masks or bounding boxes. The reliance on time-consuming human labeling effectively limits the application of these methods to problems involving very few categories. Furthermore, the human selection of the masks introduces arbitrary biases (e.g. in terms of window size and location) which may be suboptimal for classification. In this paper we propose a novel method for learning a discriminative subwindow classifier from examples annotated with binary labels indicating the presence of an object or action of interest, but not its location. During training, our approach simultaneously localizes the instances of the positive class and learns a subwindow SVM to recognize them. We extend our method to classification of time series by presenting an algorithm that localizes the most discriminative set of temporal segments in the signal. We evaluate our approach on several datasets for object and action recognition and show that it achieves results similar and in many cases superior to those obtained with full supervision.
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
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
Robust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097
Video Google: a text retrieval approach to object matching in videos
Sivic, & Zisserman (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238663 · Cited by 6,367 · cited 1×
“For quantization, we use a visual dictionary built by applying K-means clustering to a set of descriptors extracted from the training images [26].”
MethodLearning to Localize Objects with Structured Output Regression
Blaschko, M. B., & Lampert, C. H. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88682-2_2 · Cited by 324 · cited 2×
“The feature vector ϕ(x) is the histogram of visual words associated with descriptors inside rectangle x. Lampert et al. [15] showed that, when using this image representation, the search for the rectangle maximizing the SVM score can be executed efficiently by means of a branch-and-bound algorithm.”
Method
Cited by
Patch-Based Convolutional Neural Network for Whole Slide Tissue Image Classification
Hou, L., Samaras, D., Kurc, T. M., Gao, Y., Davis, J. E., & Saltz, J. H. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.266 · Cited by 866
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response
Koppula, H. S., & Saxena, A. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2430335 · Cited by 596
“Some recent effort in recognizing actions from longer video sequences take an event detection approach [15], [37], [38], [39], where they evaluate a classifier function at many different segments of the video and then predict event presence .”
BackgroundDiscriminative clustering for image co-segmentation
Joulin, A., Bach, F., & Ponce, J. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539868 · Cited by 438
Cluster-Based Co-Saliency Detection
Fu, H., Cao, X., & Tu, Z. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2260166 · Cited by 427
Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning
Cinbis, R. G., Verbeek, J., & Schmid, C. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2535231 · Cited by 420
Scene recognition and weakly supervised object localization with deformable part-based models
Pandey, M., & Lazebnik, S. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126383 · Cited by 408
Deep multiple instance learning for image classification and auto-annotation
Wu, J., Yu, Y., Huang, C., & Yu, K. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298968 · Cited by 386
Learning latent temporal structure for complex event detection
Tang, K., Fei-Fei, L., & Koller, D. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247808 · Cited by 355
Automatic Analysis of Facial Actions: A Survey
Martinez, B., Valstar, M. F., Jiang, B., & Pantic, M. (2019) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2017.2731763 · Cited by 350
Weakly Supervised Cascaded Convolutional Networks
Diba, A., Sharma, V., Pazandeh, A., Pirsiavash, H., & Van Gool, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.545 · Cited by 287
Weakly 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
Weakly Supervised Localization and Learning with Generic Knowledge
Deselaers, T., Alexe, B., & Ferrari, V. (2012) · International Journal of Computer Vision · doi:10.1007/s11263-012-0538-3 · Cited by 272
Object-Centric Spatial Pooling for Image Classification
Russakovsky, O., Lin, Y., Yu, K., & Fei-Fei, L. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33709-3_1 · Cited by 174
“[1]: the optimization framework is similar to [1] but with significantly stronger low-level descriptors (HOG descriptors [18] with LLC coding [10] compared to vector-”
BackgroundMethodInfluentialOn the Generality of Codebook Approach for Sensor-Based Human Activity Recognition
Shirahama, K., & Grzegorzek, M. (2017) · Electronics · doi:10.3390/electronics6020044 · Cited by 29
Metadata
- Authors
- Nguyen, M. H., Torresani, L., de la Torre, F., & Rother, C.
- Venue
- 2009 IEEE 12th International Conference on Computer Vision
- Publisher
- IEEE
- Published
- 2009-09
- Pages
- 1925-1932
- OpenAlex
- W2112343299
- Cited by
- 159
- References
- 5
- FWCI
- 8.45
- Type
- conference paper
- Language
- en
- Open access
- closed
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.