{"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/spatially-guiding-unsupervised-semantic","title":"Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling","arxiv_id":"2309.12378","date":"2023-09-21","proceeding":"CVPR 2024 1","authors":["Leon Sick","Dominik Engel","Pedro Hermosilla","Timo Ropinski"],"abstract":"Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learning have made significant progress on this issue and towards closing the gap to supervised algorithms. To achieve this, semantic knowledge is distilled by learning to correlate randomly sampled features from images across an entire dataset. In this work, we build upon these advances by incorporating information about the structure of the scene into the training process through the use of depth information. We achieve this by (1) learning depth-feature correlation by spatially correlate the feature maps with the depth maps to induce knowledge about the structure of the scene and (2) implementing farthest-point sampling to more effectively select relevant features by utilizing 3D sampling techniques on depth information of the scene. Finally, we demonstrate the effectiveness of our technical contributions through extensive experimentation and present significant improvements in performance across multiple benchmark datasets.","url_abs":"https://arxiv.org/abs/2309.12378v2","url_pdf":"https://arxiv.org/pdf/2309.12378v2.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":"spatially-guiding-unsupervised-semantic","repo_url":"https://github.com/leonsick/depthg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"feature-correlation","task_name":"Feature Correlation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-panoptic-segmentation","task_name":"Unsupervised Panoptic Segmentation"},{"task_slug":"unsupervised-semantic-segmentation","task_name":"Unsupervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-panoptic-segmentation-on","task":"Unsupervised Panoptic Segmentation","dataset":"Cityscapes","model":"DepthG + CutLER","rank_in_archive_order":5,"of":5,"metrics":{"PQ":"16.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco-7","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Stuff-27","model":"DepthG (ViT-B/8)","rank_in_archive_order":7,"of":29,"metrics":{"Clustering [Accuracy]":"58.6","Clustering [mIoU]":"29.0","Linear Classifier [Accuracy]":"75.5","Linear Classifier [mIoU]":"41.6"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco-7","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Stuff-27","model":"DepthG w/ 3D-LHP (ViT-S/8)","rank_in_archive_order":11,"of":29,"metrics":{"Clustering [Accuracy]":"55.1","Clustering [mIoU]":"26.7","Linear Classifier [Accuracy]":"73.9","Linear Classifier [mIoU]":"37.8"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco-7","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Stuff-27","model":"DepthG (ViT-S/8)","rank_in_archive_order":14,"of":29,"metrics":{"Clustering [Accuracy]":"56.3","Clustering [mIoU]":"25.6","Linear Classifier [Accuracy]":"73.7","Linear Classifier [mIoU]":"38.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.12378","atlas_url":"https://app.syntology.ai/?focus=2309.12378","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":"2309.12378"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2309.12378\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2309.12378"},"call":"get_concepts_for_paper(arxiv_id=\"2309.12378\")"}],"by_repo":[{"repo":"leonsick/depthg","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"eb9a5a5b7976dd979f937b984efa31b9f99eac6ae2ce95d64ca9caca462f88f4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}