{"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/st-make-self-training-work-better-for-semi","title":"ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation","arxiv_id":"2106.05095","date":"2021-06-09","proceeding":"CVPR 2022 1","authors":["Lihe Yang","Wei Zhuo","Lei Qi","Yinghuan Shi","Yang Gao"],"abstract":"Self-training via pseudo labeling is a conventional, simple, and popular pipeline to leverage unlabeled data. In this work, we first construct a strong baseline of self-training (namely ST) for semi-supervised semantic segmentation via injecting strong data augmentations (SDA) on unlabeled images to alleviate overfitting noisy labels as well as decouple similar predictions between the teacher and student. With this simple mechanism, our ST outperforms all existing methods without any bells and whistles, e.g., iterative re-training. Inspired by the impressive results, we thoroughly investigate the SDA and provide some empirical analysis. Nevertheless, incorrect pseudo labels are still prone to accumulate and degrade the performance. To this end, we further propose an advanced self-training framework (namely ST++), that performs selective re-training via prioritizing reliable unlabeled images based on holistic prediction-level stability. Concretely, several model checkpoints are saved in the first stage supervised training, and the discrepancy of their predictions on the unlabeled image serves as a measurement for reliability. Our image-level selection offers holistic contextual information for learning. We demonstrate that it is more suitable for segmentation than common pixel-wise selection. As a result, ST++ further boosts the performance of our ST. Code is available at https://github.com/LiheYoung/ST-PlusPlus.","url_abs":"https://arxiv.org/abs/2106.05095v2","url_pdf":"https://arxiv.org/pdf/2106.05095v2.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":"st-make-self-training-work-better-for-semi","repo_url":"https://github.com/LiheYoung/ST-PlusPlus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised Semantic Segmentation"}],"methods":[{"method_slug":"aware","method_name":"AWARE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.05095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05095"}},"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/LiheYoung/ST-PlusPlus","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran":1,"unverified":5},"by_repo_kind":{"official":{"samples":9,"ran":4,"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":"392d0834780485a1","entry":"ASPPConv","repo":"LiheYoung/ST-PlusPlus","repo_kind":"official","path":"model/semseg/deeplabv3plus.py","file_url":"https://github.com/LiheYoung/ST-PlusPlus/blob/HEAD/model/semseg/deeplabv3plus.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"392d0834780485a1"}},{"code_sha256_prefix":"6ef392f365cc5703","entry":"conv1x1","repo":"LiheYoung/ST-PlusPlus","repo_kind":"official","path":"model/backbone/resnet.py","file_url":"https://github.com/LiheYoung/ST-PlusPlus/blob/HEAD/model/backbone/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ef392f365cc5703"}},{"code_sha256_prefix":"794a2ed91a5175bd","entry":"conv3x3","repo":"LiheYoung/ST-PlusPlus","repo_kind":"official","path":"model/backbone/resnet.py","file_url":"https://github.com/LiheYoung/ST-PlusPlus/blob/HEAD/model/backbone/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"794a2ed91a5175bd"}},{"code_sha256_prefix":"c9896e2a9e9768ef","entry":"count_params","repo":"LiheYoung/ST-PlusPlus","repo_kind":"official","path":"utils.py","file_url":"https://github.com/LiheYoung/ST-PlusPlus/blob/HEAD/utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9896e2a9e9768ef"}},{"code_sha256_prefix":"07d14767c4ecb04a","entry":"color_map","repo":"LiheYoung/ST-PlusPlus","repo_kind":"official","path":"utils.py","file_url":"https://github.com/LiheYoung/ST-PlusPlus/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"07d14767c4ecb04a"}},{"code_sha256_prefix":"52fb4f1210c91ce6","entry":"crop","repo":"LiheYoung/ST-PlusPlus","repo_kind":"official","path":"dataset/transform.py","file_url":"https://github.com/LiheYoung/ST-PlusPlus/blob/HEAD/dataset/transform.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"52fb4f1210c91ce6"}},{"code_sha256_prefix":"49f7eaf0ab330e0d","entry":"hflip","repo":"LiheYoung/ST-PlusPlus","repo_kind":"official","path":"dataset/transform.py","file_url":"https://github.com/LiheYoung/ST-PlusPlus/blob/HEAD/dataset/transform.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49f7eaf0ab330e0d"}},{"code_sha256_prefix":"4d761942e03d5f8b","entry":"normalize","repo":"LiheYoung/ST-PlusPlus","repo_kind":"official","path":"dataset/transform.py","file_url":"https://github.com/LiheYoung/ST-PlusPlus/blob/HEAD/dataset/transform.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d761942e03d5f8b"}},{"code_sha256_prefix":"64a129d9f760a0da","entry":"resnet18","repo":"LiheYoung/ST-PlusPlus","repo_kind":"official","path":"model/backbone/resnet.py","file_url":"https://github.com/LiheYoung/ST-PlusPlus/blob/HEAD/model/backbone/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"64a129d9f760a0da"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}