{"id":13627406,"url":"https://github.com/scut-aitcm/Competitive-Inner-Imaging-SENet","last_synced_at":"2025-04-16T23:33:03.690Z","repository":{"id":217074008,"uuid":"141124150","full_name":"scut-aitcm/Competitive-Inner-Imaging-SENet","owner":"scut-aitcm","description":"Source code of paper: (not available now)","archived":false,"fork":false,"pushed_at":"2018-11-25T10:03:07.000Z","size":3885,"stargazers_count":91,"open_issues_count":1,"forks_count":11,"subscribers_count":14,"default_branch":"master","last_synced_at":"2025-02-19T01:01:56.938Z","etag":null,"topics":["attention-mechanism","computer-vision","deep-learning","mxnet","residual-networks"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/scut-aitcm.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-07-16T10:34:29.000Z","updated_at":"2024-02-14T17:05:24.000Z","dependencies_parsed_at":null,"dependency_job_id":"998f9f26-3f0a-40a1-a70f-88a5a17c3077","html_url":"https://github.com/scut-aitcm/Competitive-Inner-Imaging-SENet","commit_stats":null,"previous_names":["scut-aitcm/competitive-inner-imaging-senet","scut-aitcm/competitivesenet"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scut-aitcm%2FCompetitive-Inner-Imaging-SENet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scut-aitcm%2FCompetitive-Inner-Imaging-SENet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scut-aitcm%2FCompetitive-Inner-Imaging-SENet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scut-aitcm%2FCompetitive-Inner-Imaging-SENet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/scut-aitcm","download_url":"https://codeload.github.com/scut-aitcm/Competitive-Inner-Imaging-SENet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249288027,"owners_count":21244717,"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":["attention-mechanism","computer-vision","deep-learning","mxnet","residual-networks"],"created_at":"2024-08-01T22:00:33.745Z","updated_at":"2025-04-16T23:33:03.031Z","avatar_url":"https://github.com/scut-aitcm.png","language":"Python","funding_links":[],"categories":["\u003ca name=\"Vision\"\u003e\u003c/a\u003e2. Vision"],"sub_categories":["2.1 Image Classification"],"readme":"# Competitive-Inner-Imaging-SENet\n---\n\nSource code of paper: \n\n   **(not availbale now)** \n\n---\n## Architecture\n\n|Competitive Squeeze-Exciation Architecutre for Residual block|\n|-|\n|![architecutre](pictures/architecture.png)|\n\n---\n\nSE-ResNet module and CMPE-SE-ResNet modules:\n\n|Normal SE|Double FC squeezes|Conv 2x1 pair-view|Conv 1x1 pair-view|\n|-|-|-|-|\n|![](pictures/se_resnet_module.png)|![](pictures/cmpe_se_resnet_double_FC_squeeze.png)|![](pictures/cmpe_se_resnet_conv2x1.png)|![](pictures/cmpe_se_resnet_conv1x1.png)|\n\nThe Novel Inner-Imaging Mechanism for Channel Relation Modeling in Channel-wise Attention of ResNets (even All CNNs):\n\n|Basic Inner-Imaing Mode|Folded Inner-Imaging Mode|\n|-|-|\n|![](pictures/Basic-Inner-Imaging.png)|![](pictures/Folded-Inner-Imaging.png)|\n\n---\n\n## Requirements\n\n- **MXNet 1.2.0**\n- Python 2.7\n- CUDA 8.0+(for GPU)\n\n---\n\n## Citation\n\nnot available now\n\n---\n\n## Essential Results\nBest record of this novel model on CIFAR-10 and CIFAR-100 (used \"*mixup*\" ([https://arxiv.org/abs/1710.09412](https://arxiv.org/abs/1710.09412))) can achieve: **97.55%** and **84.38%**.\n \nThe test result on Kaggle: [CIFAR-10 - Object Recognition in Images](https://www.kaggle.com/c/cifar-10) \n\n![](pictures/cifar10_kaggle.png)\n\nInner-Imaging Examples \u0026 Channel-wise Attention Outputs\n\n![](pictures/appendix_a_fig1.png)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fscut-aitcm%2FCompetitive-Inner-Imaging-SENet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fscut-aitcm%2FCompetitive-Inner-Imaging-SENet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fscut-aitcm%2FCompetitive-Inner-Imaging-SENet/lists"}