{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T05:17:25Z","timestamp":1769318245949,"version":"3.49.0"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T00:00:00Z","timestamp":1723593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T00:00:00Z","timestamp":1723593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["No. 62222117"],"award-info":[{"award-number":["No. 62222117"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Detecting out-of-distribution (OOD) inputs plays a crucial role in guaranteeing the reliability of deep neural networks (DNNs) when deployed in real-world scenarios. However, DNNs typically exhibit overconfidence in OOD samples, which is attributed to the similarity in patterns between OOD and in-distribution (ID) samples. To mitigate this overconfidence, advanced approaches suggest the incorporation of auxiliary OOD samples during model training, where the outliers are assigned with an equal likelihood of belonging to any category. However, identifying outliers that share patterns with ID samples poses a significant challenge. To address the challenge, we propose a novel method, <jats:underline>V<\/jats:underline>irtual <jats:underline>O<\/jats:underline>utlier <jats:underline>S<\/jats:underline>m<jats:underline>o<\/jats:underline>othing (VOSo), which constructs auxiliary outliers using ID samples, thereby eliminating the need to search for OOD samples. Specifically, VOSo creates these virtual outliers by perturbing the semantic regions of ID samples and infusing patterns from other ID samples. For instance, a virtual outlier might consist of a cat\u2019s face with a dog\u2019s nose, where the cat\u2019s face serves as the semantic feature for model prediction. Meanwhile, VOSo adjusts the labels of virtual OOD samples based on the extent of semantic region perturbation, aligning with the notion that virtual outliers may contain ID patterns. Extensive experiments are conducted on diverse OOD detection benchmarks, demonstrating the effectiveness of the proposed VOSo. Our code will be available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/junz-debug\/VOSo\" ext-link-type=\"uri\">https:\/\/github.com\/junz-debug\/VOSo<\/jats:ext-link>.\n<\/jats:p>","DOI":"10.1007\/s11263-024-02210-8","type":"journal-article","created":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T07:02:23Z","timestamp":1723618943000},"page":"724-741","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Out-of-Distribution Detection with Virtual Outlier Smoothing"],"prefix":"10.1007","volume":"133","author":[{"given":"Jun","family":"Nie","sequence":"first","affiliation":[]},{"given":"Yadan","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Shanshan","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Yonggang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xinmei","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Zhen","family":"Fang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,14]]},"reference":[{"key":"2210_CR1","doi-asserted-by":"crossref","unstructured":"Bendale, A., & Boult, T. E. (2016). Towards open set deep networks. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR.2016.173"},{"key":"2210_CR2","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., & Vedaldi, A. (2014). Describing textures in the wild. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR.2014.461"},{"key":"2210_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2210_CR4","unstructured":"Djurisic, A., Bozanic, N., Ashok, A., & Liu, R. (2023). Extremely simple activation shaping for out-of-distribution detection. In International Conference on Learning Representations, ICLR."},{"key":"2210_CR5","unstructured":"Du, X., Wang, Z., Mu, C., & Li, Y. (2022). VOS: Learning what you don\u2019t know by virtual outlier synthesis. In International Conference on Learning Representations, ICLR."},{"key":"2210_CR6","unstructured":"Fang, Z., Li, Y., Jie, L., Dong, J., Han, B., & Liu, F. (2022). Is out-of-distribution detection learnable? In NeurIPS (Vol. 96, pp. 1\u20132)."},{"key":"2210_CR7","doi-asserted-by":"crossref","unstructured":"Gao, R., Zhao, C., Hong, L., & Qiang, X. (2023). Diffguard: Semantic mismatch-guided out-of-distribution detection using pre-trained diffusion models. In IEEE\/CVF International Conference on Computer Vision, ICCV.","DOI":"10.1109\/ICCV51070.2023.00152"},{"key":"2210_CR8","unstructured":"Gong, M., Zhang, K., Liu, T., Tao, D., Glymour, C., & Sch\u00f6lkopf, B. (2016). Domain adaptation with conditional transferable components. In International Conference on Machine Learning (pp. 2839\u20132848). PMLR."},{"key":"2210_CR9","unstructured":"Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017) On calibration of modern neural networks. In International Conference on Machine Learning, ICML."},{"key":"2210_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2210_CR11","doi-asserted-by":"crossref","unstructured":"Hein, M., Andriushchenko, M., & Bitterwolf, J. (2019). Why Relu networks yield high-confidence predictions far away from the training data and how to mitigate the problem. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR.2019.00013"},{"key":"2210_CR12","unstructured":"Hendrycks, D., & Dietterich, T.\u00a0G. (2019). Benchmarking neural network robustness to common corruptions and perturbations. In International Conference on Learning Representations, ICLR."},{"key":"2210_CR13","unstructured":"Hendrycks, D., & Gimpel, K. (2017). A baseline for detecting misclassified and out-of-distribution examples in neural networks. In International Conference on Learning Representations, ICLR."},{"key":"2210_CR14","unstructured":"Hendrycks, D., Mazeika, M., & Dietterich, T. G. (2019). Deep anomaly detection with outlier exposure. In International Conference on Learning Representations, ICLR (vol. 96, pp. 1\u20132)."},{"key":"2210_CR15","doi-asserted-by":"crossref","unstructured":"Horn, G.\u00a0V., Aodha, O.\u00a0M., Song, Y., Cui, Y., Sun, C., Shepard, A., Adam, H., Perona, P., & Belongie, S.\u00a0J. (2018). The inaturalist species classification and detection dataset. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR.2018.00914"},{"key":"2210_CR16","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR.2017.243"},{"key":"2210_CR17","unstructured":"Huang, R., Geng, A., & Li, Y. (2021). On the importance of gradients for detecting distributional shifts in the wild. In Advances in Neural Information Processing System. NeurIPS"},{"key":"2210_CR18","doi-asserted-by":"crossref","unstructured":"Kong, S., & Ramanan, D. (2021). Opengan: Open-set recognition via open data generation. In IEEE\/CVF International Conference on Computer Vision, ICCV.","DOI":"10.1109\/ICCV48922.2021.00085"},{"key":"2210_CR19","unstructured":"Krizhevsky, A., Hinton, G., et al. (2009). Learning multiple layers of features from tiny images. Tech Report."},{"key":"2210_CR20","unstructured":"Lee, K., Lee, K., Lee, H., & Shin, J. (2018). A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In International Conference on Learning Representations, ICLR."},{"key":"2210_CR21","unstructured":"Liang, S., Li, Y., & Srikant, R. (2018). Enhancing the reliability of out-of-distribution image detection in neural networks. In International Conference on Learning Representations, ICLR."},{"key":"2210_CR22","unstructured":"Liu, W., Wang, X., Owens, J. D., & Li, Y. (2020). Energy-based out-of-distribution detection. In Advances in Neural Information Processing Systems. NeurIPS."},{"key":"2210_CR23","unstructured":"Loshchilov, I., & Hutter, F. (2017). SGDR: Stochastic gradient descent with warm restarts. In International Conference on Learning Representations, ICLR."},{"key":"2210_CR24","unstructured":"Lukasik, M., Bhojanapalli, S., Menon, A., & Kumar, Snjiv. (2020). Does label smoothing mitigate label noise? In International Conference on Machine Learning, ICML."},{"key":"2210_CR25","unstructured":"M\u00fcller, R., Kornblith, S., & Hinton, G.\u00a0E. (2019). When does label smoothing help? In Advances in Neural Information Processing Systems, NeurIPS."},{"key":"2210_CR26","unstructured":"Nalisnick, E.\u00a0T., Matsukawa, A., Teh, Y.\u00a0W., G\u00f6r\u00fcr, D., & Lakshminarayanan, B. (2019). Do deep generative models know what they don\u2019t know? In International Conference on Learning Representations, ICLR."},{"key":"2210_CR27","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., & Ng, A.\u00a0Y. (2011). Reading digits in natural images with unsupervised feature learning. In NIPS Workshop on Deep Learning and Unsupervised Feature Learning."},{"key":"2210_CR28","doi-asserted-by":"crossref","unstructured":"Nguyen, A.\u00a0M., Yosinski, J., & Clune, J. (2015). Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"2210_CR29","doi-asserted-by":"crossref","unstructured":"Perera, P., Morariu, V.\u00a0I., Jain, R., Manjunatha, V., Wigington, C., Ordonez, V., & Patel, V.\u00a0M. (2020). Generative-discriminative feature representations for open-set recognition. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR42600.2020.01183"},{"key":"2210_CR30","unstructured":"Pereyra, G., Tucker, G., Chorowski, J., Kaiser, \u0141., & Hinton, G. (2017). Regularizing neural networks by penalizing confident output distributions. arXiv preprint arXiv:1701.06548."},{"key":"2210_CR31","unstructured":"Pinto, F., Yang, H., Lim, S.-N., Torr, P. H.\u00a0S., & Dokania, P.\u00a0K. (2022). Regmixup: Mixup as a regularizer can surprisingly improve accuracy and out distribution robustness. In Advances in Neural Information Processing System, NeurIPS."},{"key":"2210_CR32","unstructured":"Platt, J., et al. (1999). Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In Advances in Large Margin Classifiers."},{"key":"2210_CR33","unstructured":"Radford, A., Kim, J.\u00a0W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In International Conference on Machine Learning, ICML."},{"key":"2210_CR34","unstructured":"Sun, Y., Guo, C., & Li, Y. (2021). React: Out-of-distribution detection with rectified activations. In Advances in Neural Information Processing Systems. NeurIPS."},{"key":"2210_CR35","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR.2016.308"},{"key":"2210_CR36","unstructured":"Tao, L., Du, X., Zhu, J., & Li, Y. (2023). Non-parametric outlier synthesis. In International Conference on Learning Representations, ICLR (Vol. 96, pp. 1\u20132)."},{"key":"2210_CR37","unstructured":"Wang, Q., Ye, J., Liu, F., Dai, Q., Kalander, M., Liu, T., Hao, J., & Han, B. (2023). Out-of-distribution detection with implicit outlier transformation. In In International Conference on Learning Representations, ICLR."},{"key":"2210_CR38","unstructured":"Wei, H., Xie, R., Cheng, H., Feng, L., An, B., & Li, Y. (2022). Mitigating neural network overconfidence with logit normalization. In International Conference on Machine Learning, ICML."},{"key":"2210_CR39","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, James, E., Krista\u00a0A. O., & Aude, T. (2010). Antonio. SUN database: Large-scale scene recognition from abbey to zoo. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"2210_CR40","doi-asserted-by":"crossref","unstructured":"Xie, C., Tan, M., Gong, B., Wang, J., Yuille, A. L., & Quoc, V. L. (2020). Adversarial examples improve image recognition. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR42600.2020.00090"},{"key":"2210_CR41","unstructured":"Xu, P., Ehinger, K.\u00a0A., Zhang, Y., Finkelstein, A., Kulkarni, S.\u00a0R., & Xiao, J. (2015). Turkergaze: Crowdsourcing saliency with webcam based eye tracking. arXiv preprint, arXiv:1504.06755."},{"key":"2210_CR42","doi-asserted-by":"crossref","unstructured":"Yang, Y., Gao, R., & Qiang, X. (2022). Out-of-distribution detection with semantic mismatch under masking. In Proceedings of the European Conference on Computer Vision, ECCV.","DOI":"10.1007\/978-3-031-20053-3_22"},{"key":"2210_CR43","unstructured":"Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., & Xiao, J. (2015). LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint, arXiv:1506.03365."},{"key":"2210_CR44","unstructured":"Hua Yuan, Yu., Shi, N. X., Yang, X., Geng, X., & Rui, Y. (2023). Learning from biased soft labels. In Advances in Neural Information Processing Systems. NeurIPS."},{"key":"2210_CR45","doi-asserted-by":"crossref","unstructured":"Yuan, L., Tay, F. E. H., Li, G., Wang, T., & Feng, J. (2020). Revisiting knowledge distillation via label smoothing regularization. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"2210_CR46","unstructured":"Zhang, Y., Gong, M., Liu, T., Niu, G., Tian, X., Han, B., Sch\u00f6lkopf, B., & Zhang, K. (2022). Causaladv: Adversarial robustness through the lens of causality. International Conference on Learning Representations."},{"key":"2210_CR47","unstructured":"Zhang, H., Ciss\u00e9, M., Dauphin, Y. N., & Lopez-Paz, D. (2018). mixup: Beyond empirical risk minimization. In International Conference on Learning Representations, ICLR (Vol. 96, pp. 1\u20132)."},{"key":"2210_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, J., Inkawhich, N., Linderman, R., Chen, Y., & Li, H. (2023). Mixture outlier exposure: Towards out-of-distribution detection in fine-grained environments. In IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV (Vol. 96, pp. 1\u20132).","DOI":"10.1109\/WACV56688.2023.00549"},{"key":"2210_CR49","unstructured":"Zhang, J., Yang, J., Wang, P., Wang, H., Lin, Y., Zhang, H., Sun, Y., Du, X., Zhou, K., Zhang, W., et\u00a0al. (2023b). Openood v1. 5: Enhanced benchmark for out-of-distribution detection. arXiv preprint, arXiv:2306.09301"},{"key":"2210_CR50","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., & Yang, Y. (2020). Random erasing data augmentation. In In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 34, pp. 13001\u201313008).","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"2210_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, \u00c0., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR.2016.319"},{"key":"2210_CR52","doi-asserted-by":"crossref","unstructured":"Zhou, B., Lapedriza, \u00c0., Khosla, A., Oliva, A., & Torralba, A. (2018). Places: A 10 million image database for scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2017.2723009"},{"issue":"9","key":"2210_CR53","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. (2022). Learning to prompt for vision-language models. International Journal of Computer Vision, 130(9), 2337\u20132348.","journal-title":"International Journal of Computer Vision"},{"key":"2210_CR54","doi-asserted-by":"crossref","unstructured":"Zhou, Y. (2022). Rethinking reconstruction autoencoder-based out-of-distribution detection. In The IEEE\/CVF Computer Vision and Pattern Recognition Conference, CVPR.","DOI":"10.1109\/CVPR52688.2022.00723"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02210-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02210-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02210-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T06:43:32Z","timestamp":1737528212000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02210-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,14]]},"references-count":54,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["2210"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02210-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,14]]},"assertion":[{"value":"15 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}