Abstract
One of the primary challenges limiting the applicability of deep learning is its susceptibility to learning spurious correlations rather than the underlying mechanisms of the task of interest. The resulting failure to generalise cannot be addressed by simply using more data from the same distribution. We propose an auxiliary training objective that improves the generalization capabilities of neural networks by leveraging an overlooked supervisory signal found in existing datasets. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. We show that such pairs can be identified in a number of existing datasets in computer vision (visual question answering, multi-label image classification) and natural language processing (sentiment analysis, natural language inference). The new training objective orients the gradient of a model’s decision function with pairs of counterfactual examples. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
By input space, we refer to a space of feature representations of the input, i.e. vector representations (\({\varvec{x}}\)) obtained with a pretrained CNN or text encoder.
References
Abbasnejad, E., Shi, Q., van den Hengel, A., Liu, L.: A generative adversarial density estimator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)
Abbasnejad, E., Teney, D., Parvaneh, A., Shi, J., van den Hengel, A.: Counterfactual vision and language learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)
Abbasnejad, E., Wu, Q., Shi, Q., van den Hengel, A.: What’s to know? Uncertainty as a guide to asking goal-oriented questions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)
Agarwal, V., Shetty, R., Fritz, M.: Towards causal VQA: revealing and reducing spurious correlations by invariant and covariant semantic editing. arXiv preprint arXiv:1912.07538 (2019)
Agrawal, A., Batra, D., Parikh, D., Kembhavi, A.: Don’t just assume; look and answer: overcoming priors for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4971–4980 (2018)
Anderson, P., et al.: Bottom-up and top-down attention for image captioning and VQA. In: Proceedings of the CVPR (2018)
Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3674–3683 (2018)
Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE Conference on Computer Vision (2015)
Arjovsky, M., Bottou, L., Gulrajani, I., Lopez-Paz, D.: Invariant risk minimization. arXiv preprint arXiv:1907.02893 (2019)
Baradel, F., Neverova, N., Mille, J., Mori, G., Wolf, C.: CoPhy: Counterfactual learning of physical dynamics. arXiv preprint arXiv:1909.12000 (2019)
Barbu, A., et al.: ObjectNet: a large-scale bias-controlled dataset for pushing the limits of object recognition models. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 9448–9458 (2019)
Bartolo, M., Roberts, A., Welbl, J., Riedel, S., Stenetorp, P.: Beat the AI: investigating adversarial human annotations for reading comprehension. arXiv preprint arXiv:2002.00293 (2020)
Bowman, S.R., Angeli, G., Potts, C., Manning, C.D.: A large annotated corpus for learning natural language inference. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (2015)
Cadene, R., Dancette, C., Ben-younes, H., Cord, M., Parikh, D.: RUBi: reducing unimodal biases in visual question answering. arXiv preprint arXiv:1906.10169 (2019)
Camburu, O.M., Rocktäschel, T., Lukasiewicz, T., Blunsom, P.: e-SNLI: natural language inference with natural language explanations. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 9539–9549 (2018)
Chen, M., D’Arcy, M., Liu, A., Fernandez, J., Downey, D.: CODAH: an adversarially-authored question answering dataset for common sense. In: Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP, pp. 63–69 (2019)
Chen, X., et al.: Microsoft COCO captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)
Clark, C., Yatskar, M., Zettlemoyer, L.: Don’t take the easy way out: ensemble based methods for avoiding known dataset biases. arXiv preprint arXiv:1909.03683 (2019)
Teney, D., Abbasnejad, E., van den Hengel, A.: On incorporating semantic prior knowledge in deep learning through embedding-space constraints. arXiv preprint arXiv:1909.13471 (2019)
Teney, D., Abbasnejad, E., van den Hengel, A.: Unshuffling data for improved generalization. arXiv preprint arXiv:2002.11894 (2020)
Das, A., Agrawal, H., Zitnick, C.L., Parikh, D., Batra, D.: Human attention in visual question answering: do humans and deep networks look at the same regions? In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (2016)
Das, A., et al.: Visual dialog. In: Proceedings of the CVPR (2017)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Feng, S., Wallace, E., Boyd-Graber, J.: Misleading failures of partial-input baselines. arXiv preprint arXiv:1905.05778 (2019)
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17, 1–35 (2016)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. arXiv preprint arXiv:1612.00837 (2016)
Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904–6913 (2017)
Grand, G., Belinkov, Y.: Adversarial regularization for visual question answering: strengths, shortcomings, and side effects. arXiv preprint arXiv:1906.08430 (2019)
Guo, Y., Cheng, Z., Nie, L., Liu, Y., Wang, Y., Kankanhalli, M.: Quantifying and alleviating the language prior problem in visual question answering. arXiv preprint arXiv:1905.04877 (2019)
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 (2016)
Heinze-Deml, C., Meinshausen, N.: Conditional variance penalties and domain shift robustness. arXiv preprint arXiv:1710.11469 (2017)
Hendricks, L.A., Burns, K., Saenko, K., Darrell, T., Rohrbach, A.: Women also snowboard: overcoming bias in captioning models. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 793–811. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_47
Iyyer, M., Wieting, J., Gimpel, K., Zettlemoyer, L.: Adversarial example generation with syntactically controlled paraphrase networks. arXiv preprint arXiv:1804.06059 (2018)
Jakubovitz, D., Giryes, R.: Improving DNN robustness to adversarial attacks using Jacobian regularization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 525–541. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01258-8_32
Jia, R., Liang, P.: Adversarial examples for evaluating reading comprehension systems. arXiv preprint arXiv:1707.07328 (2017)
Kaushik, D., Hovy, E., Lipton, Z.C.: Learning the difference that makes a difference with counterfactually-augmented data. arXiv preprint arXiv:1909.12434 (2019)
Li, Y., Cohn, T., Baldwin, T.: Learning robust representations of text. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 1979–1985. Association for Computational Linguistics (2016)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, C., Mao, J., Sha, F., Yuille, A.: Attention correctness in neural image captioning. In: Proceedings of the Conference on AAAI (2017)
Liu, Y., et al.: CBNet: a novel composite backbone network architecture for object detection. arXiv preprint arXiv:1909.03625 (2019)
Maas, A.L., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 142–150. Association for Computational Linguistics (2011)
Mahabadi, R.K., Henderson, J.: Simple but effective techniques to reduce biases. arXiv preprint arXiv:1909.06321 (2019)
Mitchell, T.M.: The need for biases in learning generalizations. Department of Computer Science, Laboratory for Computer Science Research (1980)
Miyato, T., Dai, A.M., Goodfellow, I.: Adversarial training methods for semi-supervised text classification. arXiv preprint arXiv:1605.07725 (2016)
Moosavi-Dezfooli, S.M., Fawzi, A., Fawzi, O., Frossard, P.: Universal adversarial perturbations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1765–1773 (2017)
Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 427–436 (2015)
Ni, J., Li, J., McAuley, J.: Justifying recommendations using distantly-labeled reviews and fine-grained aspects. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 188–197. Association for Computational Linguistics (2019)
Nie, Y., Williams, A., Dinan, E., Bansal, M., Weston, J., Kiela, D.: Adversarial NLI: a new benchmark for natural language understanding. arXiv preprint arXiv:1910.14599 (2019)
Park, D.H., Darrell, T., Rohrbach, A.: Robust change captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4624–4633 (2019)
Park, D.H., Darrell, T., Rohrbach, A.: Viewpoint invariant change captioning. arXiv preprint arXiv:1901.02527 (2019)
Didelez, V., Pigeot, I.: Judea Pearl: Causality: models, reasoning, and inference. Politische Vierteljahresschrift 42(2), 313–315 (2001). https://doi.org/10.1007/s11615-001-0048-3
Peters, J., Bühlmann, P., Meinshausen, N.: Causal inference by using invariant prediction: identification and confidence intervals. J. Roy. Stat. Soc.: Ser. B (Stat. Methodol.) 78, 947–1012 (2016)
Qiao, T., Dong, J., Xu, D.: Exploring human-like attention supervision in visual question answering. In: Proceedings of the Conference on AAAI (2018)
Ramakrishnan, S., Agrawal, A., Lee, S.: Overcoming language priors in visual question answering with adversarial regularization. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 1541–1551 (2018)
Ribeiro, M.T., Singh, S., Guestrin, C.: ”Why should i trust you ?” Explaining the predictions of any classifier. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016)
Rojas-Carulla, M., Schölkopf, B., Turner, R., Peters, J.: Invariant models for causal transfer learning. J. Mach. Learn. Res. 19, 1309–1342 (2018)
Rosenthal, S., Farra, N., Nakov, P.: SemEval-2017 task 4: sentiment analysis in twitter. In: Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval 2017), pp. 502–518. Association for Computational Linguistics (2017)
Selvaraju, R.R., Das, A., Vedantam, R., Cogswell, M., Parikh, D., Batra, D.: Grad-CAM: why did you say that? arXiv preprint arXiv:1611.07450 (2016)
Selvaraju, R.R., et al.: Taking a hint: leveraging explanations to make vision and language models more grounded. In: Proceedings of the IEEE International Conference on Computer Vision (2019)
Shafahi, A., et al.: Adversarial training for free! In: Proceedings of the Advances in Neural Information Processing Systems, pp. 3353–3364 (2019)
Shetty, R.R., Fritz, M., Schiele, B.: Adversarial scene editing: automatic object removal from weak supervision. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 7706–7716 (2018)
Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)
Suhr, A., Lewis, M., Yeh, J., Artzi, Y.: A corpus of natural language for visual reasoning. In: Proceedings of the Conference on Association for Computational Linguistics, vol. 2, pp. 217–223 (2017)
Suhr, A., Zhou, S., Zhang, A., Zhang, I., Bai, H., Artzi, Y.: A corpus for reasoning about natural language grounded in photographs. arXiv preprint arXiv:1811.00491 (2018)
Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)
Teney, D., Anderson, P., He, X., van den Hengel, A.: Tips and tricks for visual question answering: learnings from the 2017 challenge. In: Proceedings of the CVPR (2018)
Teney, D., van den Hengel, A.: Zero-shot visual question answering. arXiv preprint arXiv:1611.05546 (2016)
Teney, D., van den Hengel, A.: Actively seeking and learning from live data. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Torralba, A., Efros, A.A., et al.: Unbiased look at dataset bias. In: Proceedings of the CVPR, vol. 1, p. 7 (2011)
Vapnik, V., Izmailov, R.: Rethinking statistical learning theory: learning using statistical invariants. Mach. Learn. 108, 381–423 (2019)
Vapnik, V.N.: An overview of statistical learning theory. IEEE Trans. Neural Netw. 10(5), 988–999 (1999)
Vo, N., et al.: Composing text and image for image retrieval-an empirical Odyssey. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6439–6448 (2019)
Wallace, E., Boyd-Graber, J.: Trick me if you can: adversarial writing of trivia challenge questions. In: ACL Student Research Workshop (2018)
Wang, T., Zhao, J., Yatskar, M., Chang, K.W., Ordonez, V.: Balanced datasets are not enough: estimating and mitigating gender bias in deep image representations. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5310–5319 (2019)
Williams, A., Nangia, N., Bowman, S.R.: A broad-coverage challenge corpus for sentence understanding through inference. arXiv preprint arXiv:1704.05426 (2017)
Woods, W., Chen, J., Teuscher, C.: Adversarial explanations for understanding image classification decisions and improved neural network robustness. Nat. Mach. Intell. 1(11), 508–516 (2019)
Xie, C., Tan, M., Gong, B., Wang, J., Yuille, A., Le, Q.V.: Adversarial examples improve image recognition. arXiv preprint arXiv:1911.09665 (2019)
Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Yelp: Yelp dataset challenge. http://www.yelp.com/dataset_challenge
Zellers, R., Bisk, Y., Schwartz, R., Choi, Y.: SWAG: a large-scale adversarial dataset for grounded commonsense inference. arXiv preprint arXiv:1808.05326 (2018)
Zellers, R., Holtzman, A., Bisk, Y., Farhadi, A., Choi, Y.: HellaSwag: can a machine really finish your sentence? arXiv preprint arXiv:1905.07830 (2019)
Zhang, P., Goyal, Y., Summers-Stay, D., Batra, D., Parikh, D.: Yin and Yang: balancing and answering binary visual questions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Acknowledgements
This material is based on research sponsored by Air Force Research Laboratory and DARPA under agreement number FA8750-19-2-0501. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright notation thereon.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Teney, D., Abbasnedjad, E., van den Hengel, A. (2020). Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12355. Springer, Cham. https://doi.org/10.1007/978-3-030-58607-2_34
Download citation
DOI: https://doi.org/10.1007/978-3-030-58607-2_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58606-5
Online ISBN: 978-3-030-58607-2
eBook Packages: Computer ScienceComputer Science (R0)