{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/tagger-deep-unsupervised-perceptual-grouping","title":"Tagger: Deep Unsupervised Perceptual Grouping","arxiv_id":"1606.06724","date":"2016-06-21","proceeding":"NeurIPS 2016 12","authors":["Klaus Greff","Antti Rasmus","Mathias Berglund","Tele Hotloo Hao","Jürgen Schmidhuber","Harri Valpola"],"abstract":"We present a framework for efficient perceptual inference that explicitly\nreasons about the segmentation of its inputs and features. Rather than being\ntrained for any specific segmentation, our framework learns the grouping\nprocess in an unsupervised manner or alongside any supervised task. By\nenriching the representations of a neural network, we enable it to group the\nrepresentations of different objects in an iterative manner. By allowing the\nsystem to amortize the iterative inference of the groupings, we achieve very\nfast convergence. In contrast to many other recently proposed methods for\naddressing multi-object scenes, our system does not assume the inputs to be\nimages and can therefore directly handle other modalities. For multi-digit\nclassification of very cluttered images that require texture segmentation, our\nmethod offers improved classification performance over convolutional networks\ndespite being fully connected. Furthermore, we observe that our system greatly\nimproves on the semi-supervised result of a baseline Ladder network on our\ndataset, indicating that segmentation can also improve sample efficiency.","url_abs":"http://arxiv.org/abs/1606.06724v2","url_pdf":"http://arxiv.org/pdf/1606.06724v2.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":[{"paper_slug":"tagger-deep-unsupervised-perceptual-grouping","repo_url":"https://github.com/CuriousAI/tagger","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"tagger-deep-unsupervised-perceptual-grouping","repo_url":"https://github.com/guoqikai/Deep-Unsupervised-Perceptual-Grouping","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1606.06724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.06724"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CuriousAI/tagger","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guoqikai/Deep-Unsupervised-Perceptual-Grouping","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2729579c2d2632a7","entry":"colorize_groups","repo":"CuriousAI/tagger","repo_kind":"official","path":"analyze.py","file_url":"https://github.com/CuriousAI/tagger/blob/HEAD/analyze.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2729579c2d2632a7"}},{"code_sha256_prefix":"caee0ae9be3eace4","entry":"create_fig_layout","repo":"CuriousAI/tagger","repo_kind":"official","path":"analyze.py","file_url":"https://github.com/CuriousAI/tagger/blob/HEAD/analyze.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"caee0ae9be3eace4"}},{"code_sha256_prefix":"31534c219720d12e","entry":"flatten_first_two_dims","repo":"CuriousAI/tagger","repo_kind":"official","path":"nn.py","file_url":"https://github.com/CuriousAI/tagger/blob/HEAD/nn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"31534c219720d12e"}},{"code_sha256_prefix":"7d3fdb2b81e7ad84","entry":"prepend_empty_dim","repo":"CuriousAI/tagger","repo_kind":"official","path":"nn.py","file_url":"https://github.com/CuriousAI/tagger/blob/HEAD/nn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7d3fdb2b81e7ad84"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}