{"id":19899143,"url":"https://github.com/tootouch/tootorch","last_synced_at":"2026-03-27T02:59:00.395Z","repository":{"id":62584908,"uuid":"238471770","full_name":"TooTouch/tootorch","owner":"TooTouch","description":"Implemetation XAI in Computer Vision (Pytorch)","archived":false,"fork":false,"pushed_at":"2020-03-04T08:52:14.000Z","size":8836,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-20T09:06:45.071Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/TooTouch.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-02-05T14:38:26.000Z","updated_at":"2021-10-09T20:22:32.000Z","dependencies_parsed_at":"2022-11-03T22:00:47.599Z","dependency_job_id":null,"html_url":"https://github.com/TooTouch/tootorch","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TooTouch%2Ftootorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TooTouch%2Ftootorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TooTouch%2Ftootorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TooTouch%2Ftootorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TooTouch","download_url":"https://codeload.github.com/TooTouch/tootorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252116397,"owners_count":21697372,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-12T20:07:19.148Z","updated_at":"2026-03-27T02:59:00.334Z","avatar_url":"https://github.com/TooTouch.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# tootorch\n\nImplemetation XAI in Computer Vision (Pytorch)\n\n![Hits](https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fgithub.com%2FTooTouch%2Ftootorch)\n\n# Requirements\n\n```\ntorch\nopencv-python\npillow\nh5py\ntqdm\n```\n\n# Installation\n```bash\npip install tootorch\n```\n\n# Interpretable Methods\n**Attribution Methods**\n- Vanilla Backpropagation (VBP) [[Notebook](https://github.com/Tootouch/WhiteBox-Part1/blob/master/notebook/%5BAttribution%5D%20-%20Vanilla%20Backpropagation%20%26%20Ensemble.ipynb)]\n- Input x Backpropagation (IB) [[Notebook](https://github.com/Tootouch/WhiteBox-Part1/blob/master/notebook/%5BAttribution%5D%20-%20Input%20x%20Backpropagation%20%26%20Ensemble.ipynb)]\n- DeconvNet [1] [[Notebook](https://github.com/Tootouch/WhiteBox-Part1/blob/master/notebook/%5BAttribution%5D%20-%20DeconvNet%20%26%20Ensemble.ipynb)]\n- Guided Backpropagation (GB) [2] [[Notebook](https://github.com/Tootouch/WhiteBox-Part1/blob/master/notebook/%5BAttribution%5D%20-%20Guided%20Backpropagation%20%26%20Ensemble.ipynb)]\n- Integrated Gradients (IG) [3] [[Notebook](https://github.com/Tootouch/WhiteBox-Part1/blob/master/notebook/%5BAttribution%5D%20-%20Integrated%20Gradients%20%26%20Ensemble.ipynb)]\n- Grad-CAM (GC) [4] [[Notebook](https://github.com/Tootouch/WhiteBox-Part1/blob/master/notebook/%5BAttribution%5D%20-%20GradCAM%20%26%20Ensemble.ipynb)]\n- Guided Grad-CAM (GB-GC) [4] [[Notebook](https://github.com/Tootouch/WhiteBox-Part1/blob/master/notebook/%5BAttribution%5D%20-%20Guided-GradCAM%20%26%20Ensemble.ipynb)]\n\n**Ensemble Methods**\n- SmoothGrad (SG) [5]\n- SmoothGrad-Squared (SG-SQ) [6]\n- SmoothGrad-VAR (SG-VAR) [6]\n\n# Evaluation \n- Coherence\n- Selectivity\n- Remove and Retrain (ROAR) [6]\n- Keep and Retrain (KAR) [6]\n\n# Attention Methods\n- Residual Attention Network (RAN) [7]\n- Class Activation Methods (CAM) [8]\n- Convolutional Block Attention Module (CBAM) [9]\n- Wide Attention Residual Network (WARN) [10]\n\n# Reference\n- [1] Zeiler, M. D., \u0026 Fergus, R. (2014, September). Visualizing and understanding convolutional networks. In European conference on computer vision (pp. 818-833). Springer, Cham. [[Paper](https://arxiv.org/abs/1311.2901)] [[Korean version](https://datanetworkanalysis.github.io/2019/10/27/deconvnet)]\n\n- [2] Springenberg, J. T., Dosovitskiy, A., Brox, T., \u0026 Riedmiller, M. (2014). Striving for simplicity: The all convolutional net. arXiv preprint arXiv:1412.6806. [[Paper](https://arxiv.org/abs/1412.6806)]\n\n- [3] Sundararajan, M., Taly, A., \u0026 Yan, Q. (2017, August). Axiomatic attribution for deep networks. In Proceedings of the 34th International Conference on Machine Learning-Volume 70 (pp. 3319-3328). JMLR. org. [[Paper](https://arxiv.org/pdf/1703.01365.pdf)]\n\n- [4] Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., \u0026 Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision (pp. 618-626). [[Paper](https://arxiv.org/abs/1610.02391)] [[Korean version](https://www.notion.so/tootouch/Grad-CAM-Visual-Explanations-from-Deep-Networks-via-Gradient-based-Localization-504a3f7a58fd4c3eafdc26258befd643)]\n\n- [5] Smilkov, D., Thorat, N., Kim, B., Viégas, F., \u0026 Wattenberg, M. (2017). Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825. [[Paper](\nhttps://arxiv.org/abs/1706.03825)] [[Korean version](https://datanetworkanalysis.github.io/2019/10/22/smoothgrad)]\n\n- [6] Hooker, S., Erhan, D., Kindermans, P. J., \u0026 Kim, B. (2018). Evaluating feature importance estimates. arXiv preprint arXiv:1806.10758. [[Paper](https://arxiv.org/abs/1806.10758)] [[Korean version](https://datanetworkanalysis.github.io/2019/11/13/roar_kar)]\n\n- [7]  Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., ... \u0026 Tang, X. (2017). Residual attention network for image classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 3156-3164). [[Paper](https://arxiv.org/abs/1704.06904)]\n\n- [8] Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., \u0026 Torralba, A. (2016). Learning deep features for discriminative localization. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2921-2929). [[Paper](https://arxiv.org/abs/1512.04150)]\n\n- [9]  Woo, S., Park, J., Lee, J. Y., \u0026 So Kweon, I. (2018). Cbam: Convolutional block attention module. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 3-19). [[Paper](https://arxiv.org/abs/1807.06521)]\n\n- [10] Rodríguez, P., Gonfaus, J. M., Cucurull, G., XavierRoca, F., \u0026 Gonzalez, J. (2018). Attend and rectify: a gated attention mechanism for fine-grained recovery. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 349-364). [[Paper](https://arxiv.org/abs/1807.07320)]\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftootouch%2Ftootorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftootouch%2Ftootorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftootouch%2Ftootorch/lists"}