Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts

Andrews, 2003, Support vector machines for multiple-instance learning, 577 Arun, 2019 Bianco, 2019, Multitask painting categorization by deep multibranch neural network, Expert Syst. Appl., 135, 90, 10.1016/j.eswa.2019.05.036 Bilen, 2016, Weakly supervised deep detection networks, 2846 Bongini, 2020, Visual question answering for cultural heritage Carbonneau, 2016, Multiple instance learning: A survey of problem characteristics and applications, Pattern Recognit., 77, 329, 10.1016/j.patcog.2017.10.009 Carbonneau, 2016, Robust multiple-instance learning ensembles using random subspace instance selection, Pattern Recognit., 58, 83, 10.1016/j.patcog.2016.03.035 Crowley, 2016 Crowley, 2014, In search of art, 54 Crowley, 2016, The art of detection, 721 Del Chiaro, 2019, Webly-supervised zero-shot learning for artwork instance recognition, Pattern Recognit. Lett., 128, 420, 10.1016/j.patrec.2019.09.027 Diba, 2017, Weakly supervised cascaded convolutional networks, 5131 Dietterich, 1997, Solving the multiple instance problem with axis-parallel rectangles, Artificial Intelligence, 89, 31, 10.1016/S0004-3702(96)00034-3 Donahue, 2014, DeCAF: A deep convolutional activation feature for generic visual recognition, 647 Dong, 2017, A dual-network progressive approach to weakly supervised object detection, 279 Doran, 2014, A theoretical and empirical analysis of support vector machine methods for multiple-instance classification, Mach. Learn., 97, 79, 10.1007/s10994-013-5429-5 Elgammal, 2018, The shape of art history in the eyes of the machine Everingham, 2010, The PASCAL visual object classes challenge, Int. J. Comput. Vis., 88, 303, 10.1007/s11263-009-0275-4 Felzenszwalb, 2010, Object detection with discriminatively trained part-based models, IEEE Trans. Pattern Anal. Mach. Intell., 32, 1627, 10.1109/TPAMI.2009.167 Fiorucci, 2020, Machine learning for cultural heritage: A survey, Pattern Recognit. Lett., 10.1016/j.patrec.2020.02.017 Florea, 2017, Domain transfer for delving into deep networks capacity to de-abstract art, vol. 10269, 337 Fu, 2020 Garcia, 2019, Context-aware embeddings for automatic art analysis, 25 Gehler, 2007, Deterministic annealing for multiple-instance learning, 123 Girshick, 2015, Fast R-CNN, 1440 Girshick, 2014, Rich feature hierarchies for accurate object detection and semantic segmentation, 580 Gonthier, 2018, Weakly supervised object detection in artworks, 692 Hall, 2015, Cross-depiction problem: Recognition and synthesis of photographs and artwork, Comput. Vis. Media, 1, 91, 10.1007/s41095-015-0017-1 Inoue, 2018, Cross-domain weakly-supervised object detection through progressive domain adaptation Jenicek, 2019, Linking art through human poses, 1338 Joulin, A., Bach, F., A convex relaxation for weakly supervised classifiers. In ICML, page 8. Kantorov, 2016, ContextLocNet: Context-aware deep network models for weakly supervised localization, 350 Kornblith, 2018, Do better ImageNet models transfer better?, 2661 Kuznetsova, 2020, The open images dataset V4: Unified image classification, object detection, and visual relationship detection at scale, Int. J. Comput. Vis., 10.1007/s11263-020-01316-z Lang, S., Ufer, N., Ommer, B., 2019. Finding visual patterns in artworks: An interactive search engine to detect objects in artistic images. In: DH. Lecoutre, A., Negrevergne, B., Yger, F., 2017. Recognizing Art Style Automatically in painting with deep learning. In: Asian conference on machine learning, JMLR: Workshop and Conference Proceedings, pp. 327–342. Li, 2016, Weakly supervised object localization with progressive domain adaptation, 3512 Li, 2018, Adaptive Batch Normalization for practical domain adaptation, Pattern Recognit., 80, 109, 10.1016/j.patcog.2018.03.005 Li, 2017, Deeper, broader and artier domain generalization Lin, 2014, Microsoft COCO: Common objects in context, 740 Mao, 2017, DeepArt : Learning joint representations of visual arts, 1183 Megiddo, 1988, On the complexity of polyhedral separability, Discrete Comput. Geom., 3, 325, 10.1007/BF02187916 MET, 2018 Nguyen, 2009, Weakly supervised discriminative localization and classification: a joint learning process, 1925 Noord, 2017, Learning scale-variant and scale-invariant features for deep image classification, Pattern Recognit., 61, 583, 10.1016/j.patcog.2016.06.005 Oquab, M., Bottou, L., Laptev, I., Sivic, J., 2015. Is object localization for free? - Weakly-supervised learning with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 685–694. Ramon, J., Raedt, L.D., 2000. Multi instance neural networks. In: Proceedings of the ICML-2000 Workshop on Attribute-Value and Relational Learning, pp. 53–60. Ren, 2015, Faster R-CNN: Towards real-time object detection with region proposal networks, 91 Rijksmuseum, 2018 Rosenblatt, 1958, The perceptron: A probabilistic model for information storage and organization, Psychol. Rev., 65, 386, 10.1037/h0042519 Russakovsky, 2015, ImageNet large scale visual recognition challenge, Int. J. Comput. Vis., 115, 211, 10.1007/s11263-015-0816-y Sabatelli, M., Kestemont, M., Daelemans, W., Geurts, P., 2018. Deep transfer learning for art classification problems. In: Workshop on Computer Vision for Art Analysis ECCV, Munich, pp. 1–17. Saenko, 2010, Adapting visual category models to new domains, 213 Saito, 2019 Seguin, B., Carlotta, Striolo, diLenardo, Isabella, Frederic, Kaplan, 2016. Visual link retrieval in a database of paintings. In: Computer Vision – ECCV 2016 Workshops. Seguin, 2018, New techniques for the digitization of art historical photographic archives - the case of the cini foundation in venice, Archiving Conference, 2018, 1, 10.2352/issn.2168-3204.2018.1.0.2 Shen, 2019, Discovering visual patterns in art collections with spatially-consistent feature learning Siva, 2011, Weakly supervised object detector learning with model drift detection, 343 Song, H.O., Girshick, R., Jegelka, S., Mairal, J., Harchaoui, Z., Darrell, T., 2014. On learning to localize objects with minimal supervision. In: Proceedings of the 31st International Conference on Machine Learning, vol. 32, Beijing, China, p. 9. Strezoski, 2018, OmniArt: A large-scale artistic benchmark, ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) - Spec. Sect. Deep Learn. Intell. Multimedia Anal., 14 Su, H., Deng, J., Fei-Fei, L., 2016. Crowdsourcing annotations for visual object detection. In: Workshops at the Twenty-Sixth AAAI Conference on Artificial Intelligence, p. 7. Tang, 2017, Multiple instance detection network with online instance classifier refinement, 3059 Tang, 2018, PCL: Proposal cluster learning for weakly supervised object detection, IEEE Trans. Pattern Anal. Mach. Intell. Tang, 2017, Weakly supervised learning of deformable part-based models for object detection via region proposals, IEEE Trans. Multimed., 19, 393, 10.1109/TMM.2016.2614862 Tang, P., Wang, X., Wang, A., Yan, Y., Liu, W., Huang, J., Yuille, A., 2018b. Weakly supervised region proposal network and object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 352–368. Thomas, 2018, Artistic object recognition by unsupervised style adaptation, 460 Tubaro, 2019, Micro-work, artificial intelligence and the automotive industry, J. Ind. Bus. Econ., 46, 333, 10.1007/s40812-019-00121-1 Uijlings, 2013, Selective search for object recognition, Int. J. Comput. Vis., 104, 154, 10.1007/s11263-013-0620-5 Vu, 2019, ADVENT: Adversarial entropy minimization for domain adaptation in semantic segmentation, 2517 Wan, 2019 Wan, F., Wei, P., Jiao, J., Han, Z., Ye, Q., 2018. Min-entropy latent model for weakly supervised object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1297–1306. Wang, 2018, Revisiting multiple instance neural networks, Pattern Recognit., 74, 15, 10.1016/j.patcog.2017.08.026 Westlake, 2016, Detecting people in artwork with CNNs, 825 Wilber, 2017, BAM! The behance artistic media dataset for recognition beyond photography, 1211 Yang, 2019, Unsupervised domain adaptation via disentangled representations: Application to cross-modality liver segmentation, 255 Yin, 2016, Object recognition in art drawings: Transfer of a neural network, 2299 Zhang, Y., Bai, Y., Ding, M., Li, Y., Ghanem, B., 2018b. W2F: A Weakly-supervised to fully-supervised framework for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 928–936. Zhang, 2018, Zigzag learning for weakly supervised object detection, 4262 Zhang, 2019 Zhou, Z.-H., Zhang, M.-L., 2002. Neural networks for multi-instance learning. In: Proceedings of the International Conference on Intelligent Information Technology, Beijing, China, pp. 455–459. Zhu, Y., Zhou, Y., Ye, Q., Qiu, Q., Jiao, J., 2017. Soft proposal networks for weakly supervised object localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1859–1868. Zitnick, 2014, Edge boxes: Locating object proposals from edges, vol. 8693, 391