{"url":"/method/sgpcs","slug":"sgpcs","name":"SGPCS","full_name":"Self-training Guided Prototypical Cross-domain Self-supervised learning","full_name_withheld":false,"description_markdown":"Model to adapt:\r\nWe use Ultra Fast Structure-aware Deep Lane Detection (UFLD) as baseline and strictly adopt its training scheme and hyperparameters. UFLD treats lane detection as a row-based classification problem and utilizes the row anchors defined by TuSimple.\r\n\r\nUnsupervised Domain Adaptation with SGPCS:\r\nSGPCS builds upon PCS  and performs in-domain contrastive learning and crossdomain self-supervised learning via cluster prototypes. \r\n\r\nWe reformulate the pseudo label selection mechanism from SGADA. For each lane, we select the highest confidence value from the griding cells of each row anchor. Based on their griding cell position, the confidence values are divided into two cases: absent lane points and present lane points. Thereby, the last griding cell represents absent lane points as in. For each case, we calculate the mean confidence over the corresponding lanes. We then use the thresholds defined by SGADA to decide whether the prediction is treated as a pseudo label.\r\n\r\nOur overall objective function comprises the in-domain and cross-domain loss from PCS, the losses defined by UFLD, and our adopted pseudo loss from SGADA. We adjust the momentum for memory bank feature updates to 0.5 and use spherical K-means with K = 2,500 to cluster them into prototypes.","description_state":"present","introduced_year":null,"introduced_by":{"title":"CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains","paper":"/paper/carlane-a-lane-detection-benchmark-for","first_author":"Julian Gebele","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/carlane-a-lane-detection-benchmark-for"},"source":{"url":"https://arxiv.org/abs/2206.08083v4","title":"CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Domain Adaptation","url":"/methods/category/domain-adaptation","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/carlane-a-lane-detection-benchmark-for","title":"CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains","date":"2022-06-16","arxiv_id":"2206.08083","n_code_links":1,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/2d-semantic-segmentation","name":"2D Semantic Segmentation","papers":1},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":1},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":1},{"task":"/task/lane-detection","name":"Lane Detection","papers":1},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1},{"task":"/task/unsupervised-domain-adaptation","name":"Unsupervised Domain Adaptation","papers":1},{"task":"/task/unsupervised-pre-training","name":"Unsupervised Pre-training","papers":1}],"tasks_shown":8,"n_tasks":8,"usage_by_year":[{"year":"2022","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/sgpcs"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}