DDImage: an image reduction based approach for automatically explaining black-box classifiers

• Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S (2012) Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274–2282

  Article  Google Scholar 

• Balkir E, Nejadgholi I, Fraser K, Kiritchenko S (2022) Necessity and sufficiency for explaining text classifiers: A case study in hate speech detection. In: Proceedings of the 2022 conference of the north american chapter of the association for computational linguistics: human language technologies, pp 2672–2686

• Burger M, Zeller A (2011) Minimizing reproduction of software failures. In: Proceedings of the 2011 international symposium on software testing and analysis, pp 221–231

• Burkart N, Huber MF (2021) A survey on the explainability of supervised machine learning. J Artif Intell Res 70:245–317

  Article  MathSciNet  Google Scholar 

• Carvalho DV, Pereira EM, Cardoso JS (2019) Machine learning interpretability: A survey on methods and metrics. Electronics 8(8):832

  Article  Google Scholar 

• Chandrasekaran J, Lei Y, Kacker R, Kuhn DR (2021) A combinatorial approach to explaining image classifiers. In: Proceedings of the 2021 IEEE international conference on software testing, verification and validation workshops (ICSTW), pp 35–43

• Christi A, Olson ML, Alipour MA, Groce A (2018) Reduce before you localize: Delta-debugging and spectrum-based fault localization. In: 2018 IEEE International symposium on software reliability engineering workshops (ISSREW), pp 184–191

• Cito J, Dillig I, Murali V, Chandra S (2022) Counterfactual explanations for models of code. In: Proceedings of the 44th international conference on software engineering: software engineering in practice, pp 125–134

• Clapp L, Bastani O, Anand S, Aiken A (2016) Minimizing GUI event traces. In: Proceedings of the 2016 24th ACM SIGSOFT international symposium on foundations of software engineering, pp 422–434

• Field A (2013) Discovering statistics using IBM SPSS statistics. sage

• Galhotra S, Pradhan R, Salimi B (2021) Explaining black-box algorithms using probabilistic contrastive counterfactuals. In: Proceedings of the 2021 international conference on management of data, pp 577–590

• Gilpin LH, Bau D, Yuan BZ, Bajwa A, Specter M, Kagal L (2018) Explaining explanations: An overview of interpretability of machine learning. https://doi.org/10.48550/ARXIV.1806.00069

• Goyal Y, Wu Z, Ernst J, Batra D, Parikh D, Lee S (2019) Counterfactual visual explanations. In: Proceedings of the international conference on machine learning, pp 2376–2384

• Guidotti R (2022) Counterfactual explanations and how to find them: literature review and benchmarking. Data mining and knowledge discovery pp 1–55

• Guidotti R, Monreale A, Ruggieri S, Turini F, Giannotti F, Pedreschi D (2018) A survey of methods for explaining black box models. ACM Comput Surv (CSUR) 51(5):1–42

  Article  Google Scholar 

• Hammoudi M, Burg B, Bae G, Rothermel G (2015) On the use of delta debugging to reduce recordings and facilitate debugging of web applications. In: Proceedings of the 2015 10th joint meeting on foundations of software engineering, pp 333–344

• He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. In: Proceedings of the European conference on computer vision, pp 630–645

• Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531

• Hodován R, Kiss Á, Gyimóthy T (2017) Coarse hierarchical delta debugging. In: Proceedings of the 2017 IEEE international conference on software maintenance and evolution (ICSME), pp 194–203

• Idahl M, Lyu L, Gadiraju U, Anand A (2021) Towards benchmarking the utility of explanations for model debugging. arXiv preprint arXiv:2105.04505

• Jiang M, Tang C, Zhang XY, Zhao Y, Ding Z (2023) Automated image reduction for explaining black-box classifiers. In: 2023 IEEE International conference on software analysis, evolution and reengineering (SANER), IEEE, pp 367–378

• Kim B, Khanna R, Koyejo OO (2016) Examples are not enough, learn to criticize! criticism for interpretability. Advances in neural information processing systems 29:2288–2296

• Kirschner L, Soremekun E, Zeller A (2020) Debugging inputs. In: 2020 IEEE/ACM 42nd International conference on software engineering (ICSE), IEEE, pp 75–86

• Koh PW, Liang P (2017) Understanding black-box predictions via influence functions. In: International conference on machine learning, PMLR, pp 1885–1894

• Kolesnikov A, Beyer L, Zhai X, Puigcerver J, Yung J, Gelly S, Houlsby N (2020) Big transfer (bit): General visual representation learning. In: Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part V, pp 491–507

• Kommiya Mothilal R, Mahajan D, Tan C, Sharma A (2021) Towards unifying feature attribution and counterfactual explanations: Different means to the same end. In: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, pp 652–663

• Kumar A (2022) The illustrated image captioning using transformers. ankur3107githubio. https://ankur3107.github.io/blogs/the-illustrated-image-captioning-using-transformers/

• Lertvittayakumjorn P, Toni F (2021) Explanation-based human debugging of nlp models: A survey. Transactions of the Association for Computational Linguistics 9:1508–1528

  Article  Google Scholar 

• Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, Springer, pp 740–755

• Lundberg SM, Lee SI (2017) A unified approach to interpreting model predictions. In: Proceedings of the 31st international conference on neural information processing systems, pp 4768–4777

• Martens D, Provost F (2014) Explaining data-driven document classifications. MIS quarterly 38(1):73–100

  Google Scholar 

• Mathew B, Saha P, Yimam SM, Biemann C, Goyal P, Mukherjee A (2021) Hatexplain: A benchmark dataset for explainable hate speech detection. In: Proceedings of the AAAI conference on artificial intelligence, pp 14867–14875

• Misherghi G, Su Z (2006) Hdd: hierarchical delta debugging. In: Proceedings of the 28th international conference on Software engineering, pp 142–151

• Moraffah R, Karami M, Guo R, Raglin A, Liu H (2020) Causal interpretability for machine learning-problems, methods and evaluation. ACM SIGKDD Explor Newsl 22(1):18–33

  Article  Google Scholar 

• Nguyen A, Yosinski J, Clune J (2015) Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In: 2015 IEEE Conference on computer vision and pattern recognition (CVPR), pp 427–436

• Nguyen HV, Bai L (2010) Cosine similarity metric learning for face verification. In: Proceedings of the asian conference on computer vision, pp 709–720

• Oh Y, Jung H, Park J, Kim MS (2021) Evet: enhancing visual explanations of deep neural networks using image transformations. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 3579–3587

• Olah C, Satyanarayan A, Johnson I, Carter S, Schubert L, Ye K, Mordvintsev A (2018) The building blocks of interpretability. Distill 3(3):e10

  Google Scholar 

• Papernot N, McDaniel P, Jha S, Fredrikson M, Celik ZB, Swami A (2016) The limitations of deep learning in adversarial settings. In: 2016 IEEE European symposium on security and privacy (EuroS &P), pp 372–387

• Pouyanfar S, Sadiq S, Yan Y, Tian H, Tao Y, Reyes MP, Shyu ML, Chen SC, Iyengar SS (2018) A survey on deep learning: Algorithms, techniques, and applications. ACM Comput Surv 51(5):1–36

  Article  Google Scholar 

• Qiu L, Yang Y, Cao CC, Zheng Y, Ngai H, Hsiao J, Chen L (2022) Generating perturbation-based explanations with robustness to out-of-distribution data. In: Proceedings of the ACM web conference, pp 3594–3605

• Rabin MRI, Hellendoorn VJ, Alipour MA (2021) Understanding neural code intelligence through program simplification. In: Proceedings of the 29th ACM joint meeting on european software engineering conference and symposium on the foundations of software engineering, pp 441–452

• Ribeiro MT, Singh S, Guestrin C (2016) Why should I trust you? Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 1135–1144

• Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510–4520

• Simonyan K, Vedaldi A, Zisserman A (2014) Visualising image classification models and saliency maps. Deep Inside Convolutional Networks 2:2

  Google Scholar 

• Situ X, Zukerman I, Paris C, Maruf S, Haffari G (2021) Learning to explain: Generating stable explanations fast. In: Proceedings of the 59th Annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing, pp 5340–5355

• Sun Y, Chockler H, Huang X, Kroening D (2020) Explaining image classifiers using statistical fault localization. In: European conference on computer vision, pp 391–406

• Suneja S, Zheng Y, Zhuang Y, Laredo JA, Morari A (2021) Probing model signal-awareness via prediction-preserving input minimization. In: Proceedings of the 29th ACM joint meeting on european software engineering conference and symposium on the foundations of software engineering, pp 945–955

• Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818–2826

• Tuan YL, Pryor C, Chen W, Getoor L, Wang WY (2021) Local explanation of dialogue response generation. Adv Neural Inf Process Syst 34:404–416

  Google Scholar 

• Vargha A, Delaney HD (2000) A critique and improvement of the cl common language effect size statistics of mcgraw and wong. J Educ Behav Stat 25(2):101–132

  Google Scholar 

• Vedaldi A, Soatto S (2008) Quick shift and kernel methods for mode seeking. In: Proceedings of the European conference on computer vision, Springer, pp 705–718

• Vermeire T, Brughmans D, Goethals S, de Oliveira RMB, Martens D (2022) Explainable image classification with evidence counterfactual. Pattern Anal App 1–21

• Wang G, Shen R, Chen J, Xiong Y, Zhang L (2021a) Probabilistic delta debugging. In: Proceedings of the 29th ACM joint meeting on european software engineering conference and symposium on the foundations of software engineering, pp 881–892

• Wang Y, Wang K, Wang L (2021b) Wheacha: A method for explaining the predictions of models of code. arXiv preprint arXiv:2102.04625

• Wickramanayake S, Hsu W, Lee ML (2021) Explanation-based data augmentation for image classification. Adv Neural Inf Process Syst 34:20929–20940

  Google Scholar 

• Yuan Y, Pang Q, Wang S (2022) Unveiling hidden dnn defects with decision-based metamorphic testing. In: Proceedings of the 37th IEEE/ACM international conference on automated software engineering, pp 1–13

• Zeller A (2002) Isolating cause-effect chains from computer programs. In: Proceedings of the 10th ACM SIGSOFT symposium on foundations of software engineering, pp 1–10

• Zeller A, Hildebrandt R (2002) Simplifying and isolating failure-inducing input. IEEE Trans Softw Eng 28(2):183–200

  Article  Google Scholar 

• Zhang Y, Tiňo P, Leonardis A, Tang K (2021) A survey on neural network interpretability. IEEE Trans Emerg Topics Comput Intell 5(5):726–742

  Article  Google Scholar 

• Zhao X, Huang W, Huang X, Robu V, Flynn D (2021) Baylime: Bayesian local interpretable model-agnostic explanations. In: Proceedings of the Thirty-seventh conference on uncertainty in artificial intelligence, pp 887–896

• Zhou X, Peng X, Xie T, Sun J, Li W, Ji C, Ding D (2018) Delta debugging microservice systems. In: Proceedings of the 33rd ACM/IEEE international conference on automated software engineering, pp 802–807

• Zohdinasab T, Riccio V, Tonella P (2023) An empirical study on low-and high-level explanations of deep learning misbehaviours. In: 2023 ACM/IEEE International symposium on empirical software engineering and measurement (ESEM), IEEE, pp 1–11

Download references