{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:10:18Z","timestamp":1771953018454,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":58,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609161","type":"print"},{"value":"9789819609178","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-0917-8_23","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T07:56:28Z","timestamp":1733558188000},"page":"400-417","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["ObjectCompose: Evaluating Resilience of\u00a0Vision-Based Models on\u00a0Object-to-Background Compositional Changes"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6197-3840","authenticated-orcid":false,"given":"Hashmat Shadab","family":"Malik","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9250-8096","authenticated-orcid":false,"given":"Muhammad","family":"Huzaifa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7663-7161","authenticated-orcid":false,"given":"Muzammal","family":"Naseer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9502-1749","authenticated-orcid":false,"given":"Salman","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4263-3143","authenticated-orcid":false,"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Alcorn, M.A., Li, Q., Gong, Z., Wang, C., Mai, L., Ku, W.S., Nguyen, A.: Strike (with) a pose: Neural networks are easily fooled by strange poses of familiar objects. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 4845\u20134854 (2019)","DOI":"10.1109\/CVPR.2019.00498"},{"key":"23_CR2","unstructured":"Barbu, A., Mayo, D., Alverio, J., Luo, W., Wang, C., Gutfreund, D., Tenenbaum, J., Katz, B.: Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models. Advances in neural information processing systems 32 (2019)"},{"key":"23_CR3","unstructured":"Bordes, F., Shekhar, S., Ibrahim, M., Bouchacourt, D., Vincent, P., Morcos, A.S.: Pug: Photorealistic and semantically controllable synthetic data for representation learning (2023)"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European conference on computer vision. pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"23_CR5","unstructured":"Chang, A.X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et\u00a0al.: Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Chen, H., Chen, K., Zhang, Y., Zou, Z., Shi, Z.: Diffusion models for imperceptible and transferable adversarial attack (2023)","DOI":"10.1109\/TPAMI.2024.3480519"},{"key":"23_CR7","unstructured":"Christensen, P.E., Sn\u00e6bjarnarson, V., Dittadi, A., Belongie, S., Benaim, S.: Assessing neural network robustness via adversarial pivotal tuning. arXiv preprint arXiv:2211.09782 (2022)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: Learning augmentation policies from data. arXiv preprint arXiv:1805.09501 (2018)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"23_CR9","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers. arXiv preprint arXiv:2309.16588 (2023)"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. pp. 248\u2013255. Ieee (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"23_CR11","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"23_CR12","unstructured":"Fu, Y., Zhang, S., Wu, S., Wan, C., Lin, Y.: Patch-fool: Are vision transformers always robust against adversarial perturbations? arXiv preprint arXiv:2203.08392 (2022)"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Gao, S., Li, Z.Y., Yang, M.H., Cheng, M.M., Han, J., Torr, P.: Large-scale unsupervised semantic segmentation. IEEE transactions on pattern analysis and machine intelligence (2022)","DOI":"10.1109\/TPAMI.2022.3218275"},{"key":"23_CR14","unstructured":"Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231 (2018)"},{"key":"23_CR15","unstructured":"Gondal, M.W., Wuthrich, M., Miladinovic, D., Locatello, F., Breidt, M., Volchkov, V., Akpo, J., Bachem, O., Sch\u00f6lkopf, B., Bauer, S.: On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset. Advances in Neural Information Processing Systems 32 (2019)"},{"key":"23_CR16","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"key":"23_CR17","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1109\/TSMC.1973.4309314","volume":"6","author":"RM Haralick","year":"1973","unstructured":"Haralick, R.M., Shanmugam, K., Dinstein, I.H.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. 6, 610\u2013621 (1973)","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Basart, S., Mu, N., Kadavath, S., Wang, F., Dorundo, E., Desai, R., Zhu, T., Parajuli, S., Guo, M., et\u00a0al.: The many faces of robustness: A critical analysis of out-of-distribution generalization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 8340\u20138349 (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"23_CR20","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261 (2019)"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15262\u201315271 (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"23_CR22","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"23_CR23","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)"},{"key":"23_CR24","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"23_CR26","unstructured":"Idrissi, B.Y., Bouchacourt, D., Balestriero, R., Evtimov, I., Hazirbas, C., Ballas, N., Vincent, P., Drozdzal, M., Lopez-Paz, D., Ibrahim, M.: Imagenet-x: Understanding model mistakes with factor of variation annotations. arXiv preprint arXiv:2211.01866 (2022)"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., Van Der\u00a0Maaten, L., Fei-Fei, L., Lawrence\u00a0Zitnick, C., Girshick, R.: Clevr: A diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2901\u20132910 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: Maple: Multi-modal prompt learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 19113\u201319122 (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"23_CR30","unstructured":"Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial machine learning at scale. arXiv preprint arXiv:1611.01236 (2016)"},{"key":"23_CR31","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"23_CR32","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models (2023)"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Li, X., Chen, Y., Zhu, Y., Wang, S., Zhang, R., Xue, H.: Imagenet-e: Benchmarking neural network robustness via attribute editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 20371\u201320381 (2023)","DOI":"10.1109\/CVPR52729.2023.01951"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C.L., Doll\u00e1r, P.: Microsoft coco: Common objects in context (2015)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"23_CR36","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"23_CR37","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Moayeri, M., Pope, P., Balaji, Y., Feizi, S.: A comprehensive study of image classification model sensitivity to foregrounds, backgrounds, and visual attributes (2022)","DOI":"10.1109\/CVPR52688.2022.01850"},{"key":"23_CR39","unstructured":"Naseer, M., Ranasinghe, K., Khan, S., Hayat, M., Khan, F.S., Yang, M.H.: Intriguing properties of vision transformers (2021)"},{"key":"23_CR40","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., et\u00a0al.: Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"23_CR41","unstructured":"Prabhu, V., Yenamandra, S., Chattopadhyay, P., Hoffman, J.: Lance: Stress-testing visual models by generating language-guided counterfactual images (2023)"},{"key":"23_CR42","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision (2021)"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"23_CR44","unstructured":"Rosenfeld, A., Zemel, R., Tsotsos, J.K.: The elephant in the room. arXiv preprint arXiv:1808.03305 (2018)"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Chang, H., Lee, C., Ho, J., Salimans, T., Fleet, D., Norouzi, M.: Palette: Image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings. pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"23_CR46","unstructured":"Salman, H., Ilyas, A., Engstrom, L., Kapoor, A., Madry, A.: Do adversarially robust imagenet models transfer better? (2020)"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Sharma, A., Bian, Y., Munz, P., Narayan, A.: Adversarial patch attacks and defences in vision-based tasks: A survey. arXiv preprint arXiv:2206.08304 (2022)","DOI":"10.36227\/techrxiv.20085902"},{"key":"23_CR48","doi-asserted-by":"crossref","unstructured":"Shetty, R., Schiele, B., Fritz, M.: Not using the car to see the sidewalk\u2013quantifying and controlling the effects of context in classification and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8218\u20138226 (2019)","DOI":"10.1109\/CVPR.2019.00841"},{"key":"23_CR49","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"23_CR50","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y.: Eva-clip: Improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389 (2023)"},{"key":"23_CR51","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., Fergus, R.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)"},{"key":"23_CR52","unstructured":"Xiao, K., Engstrom, L., Ilyas, A., Madry, A.: Noise or signal: The role of image backgrounds in object recognition (2020)"},{"key":"23_CR53","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: Regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"23_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, C., Pan, F., Kim, J., Kweon, I.S., Mao, C.: Imagenet-d: Benchmarking neural network robustness on diffusion synthetic object. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 21752\u201321762 (2024)","DOI":"10.1109\/CVPR52733.2024.02055"},{"key":"23_CR55","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)"},{"key":"23_CR56","unstructured":"Zhao, X., Ding, W., An, Y., Du, Y., Yu, T., Li, M., Tang, M., Wang, J.: Fast segment anything (2023)"},{"issue":"9","key":"23_CR57","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"23_CR58","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Xie, L., Yuille, A.L.: Object recognition with and without objects. arXiv preprint arXiv:1611.06596 (2016)","DOI":"10.24963\/ijcai.2017\/505"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0917-8_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T08:29:18Z","timestamp":1733560158000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0917-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609161","9789819609178"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0917-8_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}