{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:MS3NKOMCZ6GEMSIXSYSLBUM3VF","short_pith_number":"pith:MS3NKOMC","schema_version":"1.0","canonical_sha256":"64b6d53982cf8c4649179624b0d19ba941208f875122c1000e90ce2aed1c952c","source":{"kind":"arxiv","id":"1711.08506","version":1},"attestation_state":"computed","paper":{"title":"W-Net: A Deep Model for Fully Unsupervised Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian Kulis, Xide Xia","submitted_at":"2017-11-22T21:06:13Z","abstract_excerpt":"While significant attention has been recently focused on designing supervised deep semantic segmentation algorithms for vision tasks, there are many domains in which sufficient supervised pixel-level labels are difficult to obtain. In this paper, we revisit the problem of purely unsupervised image segmentation and propose a novel deep architecture for this problem. We borrow recent ideas from supervised semantic segmentation methods, in particular by concatenating two fully convolutional networks together into an autoencoder--one for encoding and one for decoding. The encoding layer produces a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1711.08506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-22T21:06:13Z","cross_cats_sorted":[],"title_canon_sha256":"2d36648175200895cbe059a86b3abe4d6666f272a1152acd7d3bc35c4ba7112b","abstract_canon_sha256":"c3e832b5e9b24c215ea22dfce143000095a722abada9e9c962326bd725a212ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:44.902200Z","signature_b64":"Nw5E1sIVOQjXlyNB2JVzYefUnA7qII62zykXrQsnVw49fw7kEEgjd37swsm+chKFQKAoJ4SQsG+YzvAt4auqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64b6d53982cf8c4649179624b0d19ba941208f875122c1000e90ce2aed1c952c","last_reissued_at":"2026-05-18T00:29:44.901631Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:44.901631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"W-Net: A Deep Model for Fully Unsupervised Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian Kulis, Xide Xia","submitted_at":"2017-11-22T21:06:13Z","abstract_excerpt":"While significant attention has been recently focused on designing supervised deep semantic segmentation algorithms for vision tasks, there are many domains in which sufficient supervised pixel-level labels are difficult to obtain. In this paper, we revisit the problem of purely unsupervised image segmentation and propose a novel deep architecture for this problem. We borrow recent ideas from supervised semantic segmentation methods, in particular by concatenating two fully convolutional networks together into an autoencoder--one for encoding and one for decoding. The encoding layer produces a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08506","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1711.08506","created_at":"2026-05-18T00:29:44.901704+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.08506v1","created_at":"2026-05-18T00:29:44.901704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08506","created_at":"2026-05-18T00:29:44.901704+00:00"},{"alias_kind":"pith_short_12","alias_value":"MS3NKOMCZ6GE","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"MS3NKOMCZ6GEMSIX","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"MS3NKOMC","created_at":"2026-05-18T12:31:31.346846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1907.01062","citing_title":"DeepTEGINN: Deep Learning Based Tools to Extract Graphs from Images of Neural Networks","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06119","citing_title":"Understanding Deep Learning Techniques for Image Segmentation","ref_index":207,"is_internal_anchor":true},{"citing_arxiv_id":"1907.10008","citing_title":"Incremental Class Discovery for Semantic Segmentation with RGBD Sensing","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2510.09833","citing_title":"Post Processing of image segmentation using Conditional Random Fields","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12391","citing_title":"Trajectory-Agnostic Asteroid Detection in TESS with Deep Learning","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04198","citing_title":"Deep Wave Network for Modeling Multi-Scale Physical Dynamics","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MS3NKOMCZ6GEMSIXSYSLBUM3VF","json":"https://pith.science/pith/MS3NKOMCZ6GEMSIXSYSLBUM3VF.json","graph_json":"https://pith.science/api/pith-number/MS3NKOMCZ6GEMSIXSYSLBUM3VF/graph.json","events_json":"https://pith.science/api/pith-number/MS3NKOMCZ6GEMSIXSYSLBUM3VF/events.json","paper":"https://pith.science/paper/MS3NKOMC"},"agent_actions":{"view_html":"https://pith.science/pith/MS3NKOMCZ6GEMSIXSYSLBUM3VF","download_json":"https://pith.science/pith/MS3NKOMCZ6GEMSIXSYSLBUM3VF.json","view_paper":"https://pith.science/paper/MS3NKOMC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.08506&json=true","fetch_graph":"https://pith.science/api/pith-number/MS3NKOMCZ6GEMSIXSYSLBUM3VF/graph.json","fetch_events":"https://pith.science/api/pith-number/MS3NKOMCZ6GEMSIXSYSLBUM3VF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MS3NKOMCZ6GEMSIXSYSLBUM3VF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MS3NKOMCZ6GEMSIXSYSLBUM3VF/action/storage_attestation","attest_author":"https://pith.science/pith/MS3NKOMCZ6GEMSIXSYSLBUM3VF/action/author_attestation","sign_citation":"https://pith.science/pith/MS3NKOMCZ6GEMSIXSYSLBUM3VF/action/citation_signature","submit_replication":"https://pith.science/pith/MS3NKOMCZ6GEMSIXSYSLBUM3VF/action/replication_record"}},"created_at":"2026-05-18T00:29:44.901704+00:00","updated_at":"2026-05-18T00:29:44.901704+00:00"}