Detector discovery in the wild: Joint multiple instance and representation learning
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
We develop methods for detector learning which exploit joint training over both weak (image-level) and strong (bounding box) labels and which transfer learned perceptual representations from strongly-labeled auxiliary tasks. Previous methods for weak-label learning often learn detector models independently using latent variable optimization, but fail to share deep representation knowledge across classes and usually require strong initialization. Other previous methods transfer deep representations from domains with strong labels to those with only weak labels, but do not optimize over individual latent boxes, and thus may miss specific salient structures for a particular category. We propose a model that subsumes these previous approaches, and simultaneously trains a representation and detectors for categories with either weak or strong labels present. We provide a novel formulation of a joint multiple instance learning method that includes examples from classification-style data when available, and also performs domain transfer learning to improve the underlying detector representation. Our model outperforms known methods on ImageNet-200 detection with weak labels.
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
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“Approaches to better optimize the non-convex problem involve using multifold learning as a measure of regularizing overfitting [8], optimize Latent SVM for the area under the ROC curve (AUC) [6] and training with easy examples in beginning to avoid bad local optimization [5, 24].”
MethodDeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019 · cited 2×
“Shortly thereafter, the feature space learned through these architectures was shown to be generic and effective for a large variety of visual recognition tasks [12, 39].”
BackgroundSelf-citationSolving 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 8×
“The major challenge faced by MIL in general is that of fixed feature representation, and poor initialization particularly in non-object centric images.”
BackgroundInfluentialAdapting visual category models to new domains
Saenko, K., Kulis, B., Fritz, M., & Darrell, T. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_16 · Cited by 2,847 · cited 1×
“Techniques to solve this problem consist of learning a new feature representation that minimizes the distance between source and target distributions [28, 23, 17, 15], regularizing the learning of a target classifier against the source model [36, 4, 9], or doing both simultaneously [20, 13].”
BackgroundSelf-citationYuille, A. L., & Rangarajan, A. (2003) · Neural Computation · doi:10.1162/08997660360581958 · Cited by 1,151 · cited 1×
“Based on this idea, Equation (1) is optimized using a classic concave-convex procedure [38], which decreases the objective value monotonically with a guarantee to converge to a local minima or saddle point.”
MethodVisualizing and Understanding Convolutional Networks
Zeiler, M. D., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1311.2901 · Cited by 522
Learning with Augmented Features for Heterogeneous Domain Adaptation
Duan, L., Xu, D., & Tsang, I. (2012) · arXiv · doi:10.48550/arxiv.1206.4660 · Cited by 320
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 10×
“The training images have fewer objects per image on an average than validation set images, so they constitute classification style data [19].”
BackgroundMethodSelf-citation
Cited by
Confident Learning: Estimating Uncertainty in Dataset Labels
Northcutt, C., Jiang, L., & Chuang, I. (2021) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12125 · Cited by 795
Multiple instance learning: A survey of problem characteristics and applications
Carbonneau, M.-A., Cheplygina, V., Granger, E., & Gagnon, G. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.10.009 · Cited by 740
“In several methods for object localization, bags are composed of many candidate bounding boxes corresponding to instances [1, 59, 130, 131, 132].”
MethodCross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation
Inoue, N., Furuta, R., Yamasaki, T., & Aizawa, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00525 · Cited by 616
Constrained Convolutional Neural Networks for Weakly Supervised Segmentation
Pathak, D., Krahenbuhl, P., & Darrell, T. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.209 · Cited by 617
Self-citationFCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
Hoffman, J., Wang, D., Yu, F., & Darrell, T. J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.02649 · Cited by 602
Self-citation
Metadata
- Authors
- Hoffman, J., Pathak, D., Darrell, T., & Saenko, K.
- Venue
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2015-06
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2155226385
- Cited by
- 75
- References
- 9
- FWCI
- 4.16
- 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.