{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/unsupervised-learning-using-pretrained-cnn","title":"Unsupervised Learning using Pretrained CNN and Associative Memory Bank","arxiv_id":"1805.01033","date":"2018-05-02","proceeding":null,"authors":["Qun Liu","Supratik Mukhopadhyay"],"abstract":"Deep Convolutional features extracted from a comprehensive labeled dataset,\ncontain substantial representations which could be effectively used in a new\ndomain. Despite the fact that generic features achieved good results in many\nvisual tasks, fine-tuning is required for pretrained deep CNN models to be more\neffective and provide state-of-the-art performance. Fine tuning using the\nbackpropagation algorithm in a supervised setting, is a time and resource\nconsuming process. In this paper, we present a new architecture and an approach\nfor unsupervised object recognition that addresses the above mentioned problem\nwith fine tuning associated with pretrained CNN-based supervised deep learning\napproaches while allowing automated feature extraction. Unlike existing works,\nour approach is applicable to general object recognition tasks. It uses a\npretrained (on a related domain) CNN model for automated feature extraction\npipelined with a Hopfield network based associative memory bank for storing\npatterns for classification purposes. The use of associative memory bank in our\nframework allows eliminating backpropagation while providing competitive\nperformance on an unseen dataset.","url_abs":"http://arxiv.org/abs/1805.01033v1","url_pdf":"http://arxiv.org/pdf/1805.01033v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-cifar100-5","task":"Few-Shot Image Classification","dataset":"CIFAR100 5-way (1-shot)","model":"UL-Hopfield (ULH)","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"89.6"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-caltech-256","task":"Few-Shot Image Classification","dataset":"Caltech-256 5-way (1-shot)","model":"UL-Hopfield (ULH)","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"74.7"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-caltech","task":"Fine-Grained Image Classification","dataset":"Caltech-101","model":"UL-Hopfield (ULH)","rank_in_archive_order":16,"of":18,"metrics":{"Accuracy":"91.00"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"UL-Hopfield (ULH)","rank_in_archive_order":240,"of":265,"metrics":{"Percentage correct":"83.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-7","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 40 Labels","model":"UL-Hopfield (ULH)","rank_in_archive_order":20,"of":21,"metrics":{"Percentage error":"16.90"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-8","task":"Semi-Supervised Image Classification","dataset":"Caltech-101","model":"UL-Hopfield (ULH)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"91.00%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-9","task":"Semi-Supervised Image Classification","dataset":"Caltech-101, 202 Labels","model":"UL-Hopfield (ULH)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"91.00%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-11","task":"Semi-Supervised Image Classification","dataset":"Caltech-256","model":"UL-Hopfield (ULH)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"77.40%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-10","task":"Semi-Supervised Image Classification","dataset":"Caltech-256, 1024 Labels","model":"UL-Hopfield (ULH)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"77.40%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.01033","atlas_url":"https://app.syntology.ai/?focus=1805.01033","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1805.01033"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1805.01033\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1805.01033"},"call":"get_concepts_for_paper(arxiv_id=\"1805.01033\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"678a8657b91e5d9c70dd4528d1fd25bde62ff90f867f2b817be71baa05d21d27","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}