{"id":13637769,"url":"https://github.com/jbeomlee93/AdvCAM","last_synced_at":"2025-04-19T17:31:41.487Z","repository":{"id":41456998,"uuid":"345585538","full_name":"jbeomlee93/AdvCAM","owner":"jbeomlee93","description":"Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation (CVPR 2021)","archived":false,"fork":false,"pushed_at":"2022-07-13T01:48:46.000Z","size":2745,"stargazers_count":124,"open_issues_count":13,"forks_count":16,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-08-03T01:11:52.655Z","etag":null,"topics":["advcam","cvpr2021","weakly-supervised-learning","weakly-supervised-segmentation"],"latest_commit_sha":null,"homepage":"","language":"Python","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/jbeomlee93.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":"2021-03-08T08:36:28.000Z","updated_at":"2024-06-22T05:17:45.000Z","dependencies_parsed_at":"2022-09-03T07:11:21.063Z","dependency_job_id":null,"html_url":"https://github.com/jbeomlee93/AdvCAM","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jbeomlee93%2FAdvCAM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jbeomlee93%2FAdvCAM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jbeomlee93%2FAdvCAM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jbeomlee93%2FAdvCAM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jbeomlee93","download_url":"https://codeload.github.com/jbeomlee93/AdvCAM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223804939,"owners_count":17205824,"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":["advcam","cvpr2021","weakly-supervised-learning","weakly-supervised-segmentation"],"created_at":"2024-08-02T01:00:30.723Z","updated_at":"2024-11-09T08:30:19.469Z","avatar_url":"https://github.com/jbeomlee93.png","language":"Python","funding_links":[],"categories":["2021"],"sub_categories":[],"readme":"# Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation\n\n\nInput Image   |  Initial CAM   | Successive Maps with adversarial climbing\n:-------------------------:|:-------------------------:|:-------------------------:\n![a](demo/2008_004430.jpg)  |  ![b](demo/2008_004430_noreg_c_idx_0_iter_0.jpg) | ![c](demo/2008_004430_gif.gif)\n\nThe implementation of Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation, Jungbeom Lee, Eunji Kim, and Sungroh Yoon, CVPR 2021. [[paper](https://arxiv.org/abs/2103.08896)]\n\n# Installation\n\n- We kindly refer to the offical implementation of [IRN](https://github.com/jiwoon-ahn/irn).\n- This repository is tested on Ubuntu 18.04, with Python 3.6, PyTorch 1.4, pydensecrf, scipy, chaniercv, imageio, and opencv-python.\n## Usage\n\n#### Step 1. Prepare Dataset\n\n- Download PASCAL VOC 2012 benchmark: [Download](https://drive.google.com/file/d/1e-yprFZzOYDAehjyMVyC5en5mNq6Mjh4/view?usp=sharing).\n\n\n#### Step 2. Prepare pre-trained classifier\n\n- Pre-trained model used in this paper: [Download](https://drive.google.com/file/d/1G0UkgjA4bndGBw2YFCrBpv71M5bj86qf/view?usp=sharing).\n- You can also train your own classifiers following [IRN](https://github.com/jiwoon-ahn/irn).\n\n\n#### Step 3. Obtain the pseudo ground-truth masks for PASCAL VOC train_aug images and evaluate them\n```\nbash get_mask_quality.sh\n```\n\n#### Step 4. Train a semantic segmentation network\n- To train DeepLab-v2, we refer to [deeplab-pytorch](https://github.com/kazuto1011/deeplab-pytorch). However, this repo contains only COCO pre-trained model. We provide [ImageNet pre-trained model](https://drive.google.com/file/d/14soMKDnIZ_crXQTlol9sNHVPozcQQpMn/view?usp=sharing) for a fair comparison with the other methods.\n\n\n## Acknowledgment\nThis code is heavily borrowed from [IRN](https://github.com/jiwoon-ahn/irn), thanks [jiwoon-ahn](https://github.com/jiwoon-ahn)!","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjbeomlee93%2FAdvCAM","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjbeomlee93%2FAdvCAM","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjbeomlee93%2FAdvCAM/lists"}