{"type":"ScholarlyArticle","title":"Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation","authors":[{"name":"Guangtao Zheng","slug":"guangtao-zheng","given":"Guangtao","family":"Zheng","affiliation":"University of Virginia"},{"name":"Wenqian Ye","slug":"wenqian-ye","given":"Wenqian","family":"Ye","affiliation":"University of Virginia"},{"name":"Aidong Zhang","slug":"aidong-zhang","given":"Aidong","family":"Zhang","affiliation":"University of Virginia"}],"abstract":"Deep neural classifiers tend to rely on spurious correlations between spurious attributes of inputs and targets to make predictions, which could jeopardize their generalization capability. Training classifiers robust to spurious correlations typically relies on annotations of spurious correlations in data, which are often expensive to get. In this paper, we tackle an annotation-free setting and propose a self-guided spurious correlation mitigation framework. Our framework automatically constructs fine-grained training labels tailored for a classifier obtained with empirical risk minimization to improve its robustness against spurious correlations. The fine-grained training labels are formulated with different prediction behaviors of the classifier identified in a novel spuriousness embedding space. We construct the space with automatically detected conceptual attributes and a novel spuriousness metric which measures how likely a class-attribute correlation is exploited for predictions.  We demonstrate that training the classifier to distinguish different prediction behaviors reduces its reliance on spurious correlations without knowing them a priori and outperforms prior methods on five real-world datasets.","doi":"10.24963/ijcai.2024/619","url":"https://ijcai.org/proceedings/2024/619","pdf":"https://ijcai.org/proceedings/2024/0619.pdf","markdown":"https://ijcai.org/proceedings/2024/619.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/619","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Machine Learning","track":"Main Track","number":619,"pages":{"first":5599,"last":5607},"keywords":["Machine Learning: ML: Robustness","Machine Learning: ML: Knowledge-aided learning"],"videos":[],"references":[{"position":1,"raw":"[Abid et al., 2022] Abubakar Abid, Mert Yuksekgonul, and James Zou. Meaningfully debugging model mistakes us- ing conceptual counterfactual explanations. In ICML, pages 66-88. PMLR, 2022.","title":"Meaningfully debugging model mistakes using conceptual counterfactual explanations","authors":"Abubakar Abid, Mert Yuksekgonul, James Zou","year":"2022","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Arjovsky et al., 2019] Martin Arjovsky, Léon Bottou, Ishaan Gulrajani, and David Lopez-Paz. Invariant risk minimization. arXiv preprint arXiv:1907.02893, 2019.","title":"Invariant risk minimization","authors":"Martin Arjovsky, Léon Bottou, Ishaan Gulrajani, David Lopez-Paz","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Asgari et al., 2022] Saeid Asgari, Aliasghar Khani, Fereshte Khani, Ali Gholami, Linh Tran, Ali Mah- davi Amiri, and Ghassan Hamarneh. Masktune: Mitigating spurious correlations by forcing to explore. NeurIPS, 35:23284-23296, 2022.","title":"Masktune: Mitigating spurious correlations by forcing to explore","authors":"Saeid Asgari, Aliasghar Khani, Fereshte Khani, Ali Gholami, Linh Tran, Ali Mahdavi Amiri, Ghassan Hamarneh","year":"2022","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bahng et al., 2020] Hyojin Bahng, Sanghyuk Chun, Sang- doo Yun, Jaegul Choo, and Seong Joon Oh. Learning de-biased representations with biased representations. In ICML, pages 528-539. PMLR, 2020.","title":"Learning de-biased representations with biased representations","authors":"Hyojin Bahng, Sanghyuk Chun, Sangdoo Yun, Jaegul Choo, Seong Joon Oh","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Beery et al., 2018] Sara Beery, Grant Van Horn, and Pietro Perona. Recognition in terra incognita. In ECCV, pages 456-473, 2018.","title":"Recognition in terra incognita","authors":"Sara Beery, Grant Van Horn, Pietro Perona","year":"2018","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Byrd and Lipton, 2019] Jonathon Byrd and Zachary Lipton. What is the effect of importance weighting in deep learn- ing? In ICML, pages 872-881. PMLR, 2019.","title":"What is the effect of importance weighting in deep learning?","authors":"Lipton Byrd, Jonathon Byrd, Zachary Lipton","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cadene et al., 2019] Remi Cadene, Corentin Dancette, Matthieu Cord, Devi Parikh, et al. Rubi: Reducing uni- modal biases for visual question answering. NeurIPS, 32, 2019.","title":"Rubi: Reducing unimodal biases for visual question answering","authors":"Cadene","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Clark et al., 2019] Christopher Clark, Mark Yatskar, and Luke Zettlemoyer. Don't take the easy way out: Ensem- ble based methods for avoiding known dataset biases. In Proceedings of the 2019 Conference on Empirical Meth- ods in Natural Language Processing and the 9th Interna- tional Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4069-4082, 2019.","title":"Don't take the easy way out: Ensemble based methods for avoiding known dataset biases","authors":"Christopher Clark, Mark Yatskar, Luke Zettlemoyer","year":"2019","venue":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Creager et al., 2021] Elliot Creager, Jörn-Henrik Jacobsen, and Richard Zemel. Environment inference for invariant learning. In ICML, pages 2189-2200. PMLR, 2021.","title":"Environment inference for invariant learning","authors":"Elliot Creager, Jörn-Henrik Jacobsen, Richard Zemel","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Cui et al., 2019] Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, and Serge Belongie. Class-balanced loss based on effective number of samples. In CVPR, pages 9268-9277, 2019.","title":"Class-balanced loss based on effective number of samples","authors":"Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, Serge Belongie","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Deng et al., 2009] Jia Deng, Wei Dong, Richard Socher, Li- Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In CVPR, pages 248-255, 2009.","title":"Imagenet: A large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Deng et al., 2023] Yihe Deng, Yu Yang, Baharan Mirza- soleiman, and Quanquan Gu. Robust learning with pro- gressive data expansion against spurious correlation. arXiv preprint arXiv:2306.04949, 2023.","title":"Robust learning with progressive data expansion against spurious correlation","authors":"Yihe Deng, Yu Yang, Baharan Mirzasoleiman, Quanquan Gu","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Dosovitskiy et al., 2020] Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Min- derer, Georg Heigold, Sylvain Gelly, et al. An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR, 2020.","title":"An image is worth 16x16 words: Transformers for image recognition at scale","authors":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Geirhos et al., 2018] Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A Wichmann, and Wieland Brendel. Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231, 2018.","title":"Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness","authors":"Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A Wichmann, Wieland Brendel","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Geirhos et al., 2019] Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A. Wichmann, and Wieland Brendel. Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In ICLR, 2019.","title":"Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","authors":"Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A Wichmann, Wieland Brendel","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Geirhos et al., 2020] Robert Geirhos, Jörn-Henrik Jacob- sen, Claudio Michaelis, Richard Zemel, Wieland Brendel, Matthias Bethge, and Felix A Wichmann. Shortcut learn- ing in deep neural networks. Nature Machine Intelligence, 2(11):665-673, 2020.","title":"Shortcut learning in deep neural networks","authors":"Robert Geirhos, Jörn-Henrik Jacobsen, Claudio Michaelis, Richard Zemel, Wieland Brendel, Matthias Bethge, Felix A Wichmann","year":"2020","venue":"Nature Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Han et al., 2022] Zongbo Han, Zhipeng Liang, Fan Yang, Liu Liu, Lanqing Li, Yatao Bian, Peilin Zhao, Bingzhe Wu, Changqing Zhang, and Jianhua Yao. Umix: Im- proving importance weighting for subpopulation shift via uncertainty-aware mixup. NeurIPS, 35:37704-37718, 2022.","title":"Umix: Improving importance weighting for subpopulation shift via uncertainty-aware mixup","authors":"Han","year":"2022","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[He and Garcia, 2009] Haibo He and Edwardo A Garcia. Learning from imbalanced data. IEEE Transactions on knowledge and data engineering, 21(9):1263-1284, 2009.","title":"Learning from imbalanced data","authors":"Haibo He, Edwardo A Garcia","year":"2009","venue":"IEEE Transactions on knowledge and data engineering","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[He et al., 2021] Yue He, Zheyan Shen, and Peng Cui. To- wards non-iid image classification: A dataset and base- lines. Pattern Recognition, 110:107383, 2021.","title":"Towards non-iid image classification: A dataset and baselines","authors":"Yue He, Zheyan Shen, Peng Cui","year":"2021","venue":"Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Hendrycks et al., 2021] Dan Hendrycks, Kevin Zhao, Steven Basart, Jacob Steinhardt, and Dawn Song. Natural adversarial examples. In CVPR, pages 15262-15271, 2021.","title":"Natural adversarial examples","authors":"Dan Hendrycks, Kevin Zhao, Steven Basart, Jacob Steinhardt, Dawn Song","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Izmailov et al., 2022] Pavel Izmailov, Polina Kirichenko, Nate Gruver, and Andrew G Wilson. On feature learning in the presence of spurious correlations. NeurIPS, 35:38516- 38532, 2022.","title":"On feature learning in the presence of spurious correlations","authors":"Pavel Izmailov, Polina Kirichenko, Nate Gruver, Andrew G Wilson","year":"2022","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Kim et al., 2022] Nayeong Kim, Sehyun Hwang, Sungsoo Ahn, Jaesik Park, and Suha Kwak. Learning debiased clas- sifier with biased committee. NeurIPS, 35:18403-18415, 2022.","title":"Learning debiased classifier with biased committee","authors":"Kim","year":"2022","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Kirichenko et al., 2023] Polina Kirichenko, Pavel Izmailov, and Andrew Gordon Wilson. Last layer re-training is suf- ficient for robustness to spurious correlations. In ICLR, 2023.","title":"Last layer re-training is sufficient for robustness to spurious correlations","authors":"Polina Kirichenko, Pavel Izmailov, Andrew Gordon, Wilson","year":"2023","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Lee et al., 2022] Yoonho Lee, Huaxiu Yao, and Chelsea Finn. Diversify and disambiguate: Out-of-distribution ro- bustness via disagreement. In ICLR, 2022.","title":"Diversify and disambiguate: Out-of-distribution robustness via disagreement","authors":"Lee","year":"2022","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Levy et al., 2020] Daniel Levy, Yair Carmon, John C Duchi, and Aaron Sidford. Large-scale methods for distribution- ally robust optimization. NeurIPS, 33:8847-8860, 2020.","title":"Large-scale methods for distributionally robust optimization","authors":"Daniel Levy, Yair Carmon, John C Duchi, Aaron Sidford","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Liu et al., 2015] Ziwei Liu, Ping Luo, Xiaogang Wang, and Xiaoou Tang. Deep learning face attributes in the wild. In ICCV, pages 3730-3738, 2015.","title":"Deep learning face attributes in the wild","authors":"Ziwei Liu, Ping Luo, Xiaogang Wang, Xiaoou Tang","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Liu et al., 2021] Evan Z Liu, Behzad Haghgoo, Annie S Chen, Aditi Raghunathan, Pang Wei Koh, Shiori Sagawa, Percy Liang, and Chelsea Finn. Just train twice: Improv- ing group robustness without training group information. In ICML, pages 6781-6792. PMLR, 2021.","title":"Just train twice: Improving group robustness without training group information","authors":"Evan Z Liu, Behzad Haghgoo, Annie S Chen, Aditi Raghunathan, Pang Wei Koh, Shiori Sagawa, Percy Liang, Chelsea Finn","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Nam et al., 2020] Junhyun Nam, Hyuntak Cha, Sungsoo Ahn, Jaeho Lee, and Jinwoo Shin. Learning from fail- ure: De-biasing classifier from biased classifier. NeurIPS, 33:20673-20684, 2020.","title":"Learning from failure: De-biasing classifier from biased classifier","authors":"Nam","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Nam et al., 2022] Junhyun Nam, Jaehyung Kim, Jaeho Lee, and Jinwoo Shin. Spread spurious attribute: Improving worst-group accuracy with spurious attribute estimation. In ICLR, 2022.","title":"Spread spurious attribute: Improving worst-group accuracy with spurious attribute estimation","authors":"Nam","year":"2022","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Nauta et al., 2021] Meike Nauta, Ricky Walsh, Adam Dubowski, and Christin Seifert. Uncovering and correct- ing shortcut learning in machine learning models for skin cancer diagnosis. Diagnostics, 12(1):40, 2021.","title":"Uncovering and correcting shortcut learning in machine learning models for skin cancer diagnosis","authors":"Meike Nauta, Ricky Walsh, Adam Dubowski, Christin Seifert","year":"2021","venue":"Diagnostics","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Neuhaus et al., 2022] Yannic Neuhaus, Maximilian Au- gustin, Valentyn Boreiko, and Matthias Hein. Spuri- ous features everywhere-large-scale detection of harm- ful spurious features in imagenet. arXiv preprint arXiv:2212.04871, 2022.","title":"Spurious features everywhere-large-scale detection of harmful spurious features in imagenet","authors":"Yannic Neuhaus, Maximilian Augustin, Valentyn Boreiko, Matthias Hein","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[NLP Connect, 2022] NLP Connect. vit-gpt2-image- captioning (revision 0e334c7), 2022.","title":"NLP Connect. vit-gpt2-imagecaptioning","authors":"Nlp Connect","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Nushi et al., 2018] Besmira Nushi, Ece Kamar, and Eric Horvitz. Towards accountable ai: Hybrid human-machine analyses for characterizing system failure. In Proceed- ings of the AAAI Conference on Human Computation and Crowdsourcing, volume 6, pages 126-135, 2018.","title":"Towards accountable ai: Hybrid human-machine analyses for characterizing system failure","authors":"Nushi","year":"2018","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Plumb et al., 2022] Gregory Plumb, Marco Tulio Ribeiro, and Ameet Talwalkar. Finding and fixing spurious patterns with explanations. Transactions on Machine Learning Re- search, 2022. Expert Certification.","title":"Finding and fixing spurious patterns with explanations","authors":"Gregory Plumb, Marco Tulio Ribeiro, Ameet Talwalkar","year":"2022","venue":"Transactions on Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Radford et al., 2019] Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019.","title":"Language models are unsupervised multitask learners","authors":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever","year":"2019","venue":"OpenAI blog","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Sagawa et al., 2019] Shiori Sagawa, Pang Wei Koh, Tat- sunori B Hashimoto, and Percy Liang. Distributionally robust neural networks. In ICLR, 2019.","title":"Distributionally robust neural networks","authors":"Shiori Sagawa, Pang Wei Koh, Tatsunori B Hashimoto, Percy Liang","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Sagawa et al., 2020] Shiori Sagawa, Aditi Raghunathan, Pang Wei Koh, and Percy Liang. An investigation of why overparameterization exacerbates spurious correlations. In ICML, pages 8346-8356. PMLR, 2020.","title":"An investigation of why overparameterization exacerbates spurious correlations","authors":"Shiori Sagawa, Aditi Raghunathan, Pang Wei Koh, Percy Liang","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Singla and Feizi, 2021] Sahil Singla and Soheil Feizi. Salient imagenet: How to discover spurious features in deep learning? In ICLR, 2021.","title":"Salient imagenet: How to discover spurious features in deep learning?","authors":"Feizi Singla, Sahil Singla, Soheil Feizi","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Wang et al., 2021] Tan Wang, Chang Zhou, Qianru Sun, and Hanwang Zhang. Causal attention for unbiased visual recognition. In ICCV, pages 3091-3100, 2021.","title":"Causal attention for unbiased visual recognition","authors":"Tan Wang, Chang Zhou, Qianru Sun, Hanwang Zhang","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Welinder et al., 2010] P. Welinder, S. Branson, T. Mita, C. Wah, F. Schroff, S. Belongie, and P. Perona. Caltech- UCSD Birds 200. Technical Report CNS-TR-2010-001, California Institute of Technology, 2010.","title":null,"authors":"P Welinder, S Branson, T Mita, C Wah, F Schroff, S Belongie, P Perona","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Woo et al., 2018] Sanghyun Woo, Jongchan Park, Joon- Young Lee, and In So Kweon. Cbam: Convolutional block attention module. In ECCV, pages 3-19, 2018.","title":"Cbam: Convolutional block attention module","authors":"Sanghyun Woo, Jongchan Park, Joon-Young Lee, In So Kweon","year":"2018","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Wu et al., 2023] Shirley Wu, Mert Yuksekgonul, Linjun Zhang, and James Zou. Discover and cure: Concept- aware mitigation of spurious correlation. arXiv preprint arXiv:2305.00650, 2023.","title":"Discover and cure: Conceptaware mitigation of spurious correlation","authors":"Shirley Wu, Mert Yuksekgonul, Linjun Zhang, James Zou","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Xiao et al., 2021] Kai Yuanqing Xiao, Logan Engstrom, Andrew Ilyas, and Aleksander Madry. Noise or signal: The role of image backgrounds in object recognition. In ICLR, 2021.","title":"Noise or signal: The role of image backgrounds in object recognition","authors":"Kai Yuanqing, Xiao, Logan Engstrom, Andrew Ilyas, Aleksander Madry","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Yao et al., 2022] Huaxiu Yao, Yu Wang, Sai Li, Linjun Zhang, Weixin Liang, James Zou, and Chelsea Finn. Im- proving out-of-distribution robustness via selective aug- mentation. In ICML, pages 25407-25437. PMLR, 2022.","title":"Improving out-of-distribution robustness via selective augmentation","authors":"Huaxiu Yao, Yu Wang, Sai Li, Linjun Zhang, Weixin Liang, James Zou, Chelsea Finn","year":"2022","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Zhang et al., 2018a] Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. mixup: Beyond empirical risk minimization. In ICLR, 2018.","title":"mixup: Beyond empirical risk minimization","authors":"Zhang","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Zhang et al., 2018b] Jiawei Zhang, Yang Wang, Piero Molino, Lezhi Li, and David S Ebert. Manifold: A model- agnostic framework for interpretation and diagnosis of ma- chine learning models. IEEE transactions on visualization and computer graphics, 25(1):364-373, 2018.","title":"Manifold: A modelagnostic framework for interpretation and diagnosis of machine learning models","authors":"Zhang","year":"2018","venue":"IEEE transactions on visualization and computer graphics","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Zhang et al., 2022] Michael Zhang, Nimit S Sohoni, Hongyang R Zhang, Chelsea Finn, and Christopher Re. Correct-n-contrast: a contrastive approach for improving robustness to spurious correlations. In Kamalika Chaud- huri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato, editors, Proceedings of the 39th International Conference on Machine Learning, volume 162 of Proceedings of Machine Learning Research, pages 26484-26516. PMLR, 17-23 Jul 2022.","title":"Correct-n-contrast: a contrastive approach for improving robustness to spurious correlations","authors":"Michael Zhang, S Nimit, Sohoni, Chelsea Hongyang R Zhang, Christopher Finn, Re","year":"2022","venue":"Proceedings of the 39th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Zhou et al., 2017] Bolei Zhou, Agata Lapedriza, Aditya Khosla, Aude Oliva, and Antonio Torralba. Places: A 10 million image database for scene recognition. IEEE transactions on pattern analysis and machine intelligence, 40(6):1452-1464, 2017.","title":"Places: A 10 million image database for scene recognition","authors":"Zhou","year":"2017","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}