{"id":21643694,"url":"https://github.com/akshayxml/corrmcnn","last_synced_at":"2026-04-13T11:02:20.602Z","repository":{"id":69055010,"uuid":"355533982","full_name":"akshayxml/CorrMCNN","owner":"akshayxml","description":"Implementation of 'Common Representation Learning Using Step-basedCorrelation Multi-Modal CNN' paper.","archived":false,"fork":false,"pushed_at":"2021-05-04T06:02:19.000Z","size":22004,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-19T08:49:15.721Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/akshayxml.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}},"created_at":"2021-04-07T12:19:17.000Z","updated_at":"2021-05-04T06:57:30.000Z","dependencies_parsed_at":null,"dependency_job_id":"c7c4a9c3-fc86-4361-aee1-ef6c5f089518","html_url":"https://github.com/akshayxml/CorrMCNN","commit_stats":null,"previous_names":["akshayxml/corrmcnn"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/akshayxml/CorrMCNN","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akshayxml%2FCorrMCNN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akshayxml%2FCorrMCNN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akshayxml%2FCorrMCNN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akshayxml%2FCorrMCNN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/akshayxml","download_url":"https://codeload.github.com/akshayxml/CorrMCNN/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akshayxml%2FCorrMCNN/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31749765,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T09:16:15.125Z","status":"ssl_error","status_checked_at":"2026-04-13T09:16:05.023Z","response_time":93,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":"2024-11-25T05:35:34.550Z","updated_at":"2026-04-13T11:02:20.587Z","avatar_url":"https://github.com/akshayxml.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Common Representation Learning using Step-based Correlation Multi-Modal CNN\n\nImplementation of the paper *[Common Representation Learning Using Step-based Correlation Multi-Modal CNN](https://arxiv.org/pdf/1711.00003.pdf)* using both Keras and Pytorch.\n\n# Aim\nTo make a novel step-based correlation multi-modal CNN(CorrMCNN) which reconstructs one view of the data given the other while increasing the interaction between the representations at each hidden layer or every intermediate step.\n\n# Dataset\n\n- MNIST handwritten digits dataset -60,000 images for training and 10,000 for testing.\n- Each image is split vertically into two halves so as to obtain an image of 28 x 14 = 392 features\n![Dataset](https://github.com/AkshayViru/CorrMCNN/blob/main/images/dataset.png)\n\n# Technique: Deep Autoencoder based Approach\nMulti-Modal Autoencoder is used which is two channeled AE that performs 2 types of reconstructions which provide the ability to adapt towards transfer learning tasks:\n- Self-reconstruction of view from itself.\n- Cross-reconstruction where one view is reconstructed given the other.\n\n# Implementation\nThis research paper is an improvement over the *[Correlational Neural Networks](https://arxiv.org/pdf/1504.07225.pdf)* paper with the following additions:\n- Introduced convolution layer in the encoding phase and deconvolution layer in the decoding stage of the Correlation multi-modal CNN(CorrMCNN)\n- Batch Normalization in the intermediate layers\n- Instead of using final hidden representations in the correlation loss, correlation is computed at each intermediate layer.\n\n# Architecture\n![CorrMCNN Architecture](https://github.com/AkshayViru/CorrMCNN/blob/main/images/architecture.png)\n\n# Results\n![CorrMCNN Architecture](https://github.com/AkshayViru/CorrMCNN/blob/main/images/results_1.JPG)\n![CorrMCNN Architecture](https://github.com/AkshayViru/CorrMCNN/blob/main/images/results_2.JPG)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fakshayxml%2Fcorrmcnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fakshayxml%2Fcorrmcnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fakshayxml%2Fcorrmcnn/lists"}