{"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/not-all-pixels-are-equal-difficulty-aware","title":"Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade","arxiv_id":"1704.01344","date":"2017-04-05","proceeding":"CVPR 2017 7","authors":["Xiaoxiao Li","Ziwei Liu","Ping Luo","Chen Change Loy","Xiaoou Tang"],"abstract":"We propose a novel deep layer cascade (LC) method to improve the accuracy and\nspeed of semantic segmentation. Unlike the conventional model cascade (MC) that\nis composed of multiple independent models, LC treats a single deep model as a\ncascade of several sub-models. Earlier sub-models are trained to handle easy\nand confident regions, and they progressively feed-forward harder regions to\nthe next sub-model for processing. Convolutions are only calculated on these\nregions to reduce computations. The proposed method possesses several\nadvantages. First, LC classifies most of the easy regions in the shallow stage\nand makes deeper stage focuses on a few hard regions. Such an adaptive and\n'difficulty-aware' learning improves segmentation performance. Second, LC\naccelerates both training and testing of deep network thanks to early decisions\nin the shallow stage. Third, in comparison to MC, LC is an end-to-end trainable\nframework, allowing joint learning of all sub-models. We evaluate our method on\nPASCAL VOC and Cityscapes datasets, achieving state-of-the-art performance and\nfast speed.","url_abs":"http://arxiv.org/abs/1704.01344v1","url_pdf":"http://arxiv.org/pdf/1704.01344v1.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":"not-all-pixels-are-equal-difficulty-aware","repo_url":"https://github.com/liuziwei7/region-conv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"Deep Layer Cascade (LC)","rank_in_archive_order":23,"of":51,"metrics":{"Mean IoU":"82.7%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.01344","atlas_url":"https://app.syntology.ai/?focus=1704.01344","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":"1704.01344"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1704.01344\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1704.01344"},"call":"get_concepts_for_paper(arxiv_id=\"1704.01344\")"}],"by_repo":[{"repo":"liuziwei7/region-conv","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":"a407dc62fbd0f02cca304e8546d4a44f88ed8d5e252ecad6c971296aec6a35a4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}