{"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/instance-level-human-parsing-via-part","title":"Instance-level Human Parsing via Part Grouping Network","arxiv_id":"1808.00157","date":"2018-08-01","proceeding":"ECCV 2018 9","authors":["Ke Gong","Xiaodan Liang","Yicheng Li","Yimin Chen","Ming Yang","Liang Lin"],"abstract":"Instance-level human parsing towards real-world human analysis scenarios is\nstill under-explored due to the absence of sufficient data resources and\ntechnical difficulty in parsing multiple instances in a single pass. Several\nrelated works all follow the \"parsing-by-detection\" pipeline that heavily\nrelies on separately trained detection models to localize instances and then\nperforms human parsing for each instance sequentially. Nonetheless, two\ndiscrepant optimization targets of detection and parsing lead to suboptimal\nrepresentation learning and error accumulation for final results. In this work,\nwe make the first attempt to explore a detection-free Part Grouping Network\n(PGN) for efficiently parsing multiple people in an image in a single pass. Our\nPGN reformulates instance-level human parsing as two twinned sub-tasks that can\nbe jointly learned and mutually refined via a unified network: 1) semantic part\nsegmentation for assigning each pixel as a human part (e.g., face, arms); 2)\ninstance-aware edge detection to group semantic parts into distinct person\ninstances. Thus the shared intermediate representation would be endowed with\ncapabilities in both characterizing fine-grained parts and inferring instance\nbelongings of each part. Finally, a simple instance partition process is\nemployed to get final results during inference. We conducted experiments on\nPASCAL-Person-Part dataset and our PGN outperforms all state-of-the-art\nmethods. Furthermore, we show its superiority on a newly collected multi-person\nparsing dataset (CIHP) including 38,280 diverse images, which is the largest\ndataset so far and can facilitate more advanced human analysis. The CIHP\nbenchmark and our source code are available at http://sysu-hcp.net/lip/.","url_abs":"http://arxiv.org/abs/1808.00157v1","url_pdf":"http://arxiv.org/pdf/1808.00157v1.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":"instance-level-human-parsing-via-part","repo_url":"https://github.com/Engineering-Course/CIHP_PGN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"edge-detection","task_name":"Edge Detection"},{"task_slug":"human-parsing","task_name":"Human Parsing"},{"task_slug":"human-part-segmentation","task_name":"Human Part Segmentation"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[{"slug":"cihp","name":"CIHP","full_name":"Crowd Instance-level Human Parsing"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-part-segmentation-on-cihp","task":"Human Part Segmentation","dataset":"CIHP","model":"PGN + ResNet101","rank_in_archive_order":6,"of":6,"metrics":{"Mean IoU":"55.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.00157","atlas_url":"https://app.syntology.ai/?focus=1808.00157","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.00157"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/Engineering-Course/CIHP_PGN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":14},"by_repo_kind":{"official":{"samples":14,"ran":0,"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":"c598804162457140","entry":"average_gradients","repo":"Engineering-Course/CIHP_PGN","repo_kind":"official","path":"train_pgn.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/train_pgn.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":"c598804162457140"}},{"code_sha256_prefix":"285297765b0a1be2","entry":"conv2d","repo":"Engineering-Course/CIHP_PGN","repo_kind":"official","path":"utils/ops.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/utils/ops.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":"285297765b0a1be2"}},{"code_sha256_prefix":"f0cb824658baf378","entry":"get_filter_output_shape","repo":"Engineering-Course/CIHP_PGN","repo_kind":"official","path":"kaffe/shapes.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/kaffe/shapes.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":"f0cb824658baf378"}},{"code_sha256_prefix":"619139704cd246c3","entry":"get_strided_kernel_output_shape","repo":"Engineering-Course/CIHP_PGN","repo_kind":"official","path":"kaffe/shapes.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/kaffe/shapes.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":"619139704cd246c3"}},{"code_sha256_prefix":"2496574c6a643967","entry":"image_mirroring","repo":"Engineering-Course/CIHP_PGN","repo_kind":"official","path":"utils/image_reader_pgn.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/utils/image_reader_pgn.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":"2496574c6a643967"}},{"code_sha256_prefix":"b73f410e9cae7cf2","entry":"image_mirroring","repo":"Engineering-Course/CIHP_PGN","repo_kind":"official","path":"utils/image_reade_inf.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/utils/image_reade_inf.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":"b73f410e9cae7cf2"}},{"code_sha256_prefix":"b5ac15f02ef566e4","entry":"image_mirroring","repo":"Engineering-Course/CIHP_PGN","repo_kind":"official","path":"utils/image_reader.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/utils/image_reader.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":"b5ac15f02ef566e4"}},{"code_sha256_prefix":"05a080c8a7d0297f","entry":"image_scaling","repo":"Engineering-Course/CIHP_PGN","repo_kind":"official","path":"utils/image_reader_pgn.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/utils/image_reader_pgn.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":"05a080c8a7d0297f"}},{"code_sha256_prefix":"846c829b29a2563c","entry":"image_scaling","repo":"Engineering-Course/CIHP_PGN","repo_kind":"official","path":"utils/image_reade_inf.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/utils/image_reade_inf.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":"846c829b29a2563c"}},{"code_sha256_prefix":"fab32b621c712604","entry":"layer","repo":"Engineering-Course/CIHP_PGN","repo_kind":"official","path":"kaffe/tensorflow/network.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/kaffe/tensorflow/network.py","link_basis":"harvester_set","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":"fab32b621c712604"}},{"code_sha256_prefix":"b2a7ddf5cb874b47","entry":"linear","repo":"Engineering-Course/CIHP_PGN","repo_kind":"official","path":"utils/ops.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/utils/ops.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":"b2a7ddf5cb874b47"}},{"code_sha256_prefix":"bfae8c1c80fbeb1c","entry":"max_pool","repo":"Engineering-Course/CIHP_PGN","repo_kind":"official","path":"utils/ops.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/utils/ops.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":"bfae8c1c80fbeb1c"}},{"code_sha256_prefix":"b874fe7b2d022945","entry":"random_resize_img_labels","repo":"Engineering-Course/CIHP_PGN","repo_kind":"official","path":"utils/image_reader_pgn.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/utils/image_reader_pgn.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":"b874fe7b2d022945"}},{"code_sha256_prefix":"f9387ac8956d5501","entry":"shape_identity","repo":"Engineering-Course/CIHP_PGN","repo_kind":"official","path":"kaffe/shapes.py","file_url":"https://github.com/Engineering-Course/CIHP_PGN/blob/HEAD/kaffe/shapes.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":"f9387ac8956d5501"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}