{"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/inverted-pyramid-multi-task-transformer-for","title":"InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding","arxiv_id":"2203.07997","date":"2022-03-15","proceeding":null,"authors":["Hanrong Ye","Dan Xu"],"abstract":"Multi-task dense scene understanding is a thriving research domain that requires simultaneous perception and reasoning on a series of correlated tasks with pixel-wise prediction. Most existing works encounter a severe limitation of modeling in the locality due to heavy utilization of convolution operations, while learning interactions and inference in a global spatial-position and multi-task context is critical for this problem. In this paper, we propose a novel end-to-end Inverted Pyramid multi-task Transformer (InvPT) to perform simultaneous modeling of spatial positions and multiple tasks in a unified framework. To the best of our knowledge, this is the first work that explores designing a transformer structure for multi-task dense prediction for scene understanding. Besides, it is widely demonstrated that a higher spatial resolution is remarkably beneficial for dense predictions, while it is very challenging for existing transformers to go deeper with higher resolutions due to huge complexity to large spatial size. InvPT presents an efficient UP-Transformer block to learn multi-task feature interaction at gradually increased resolutions, which also incorporates effective self-attention message passing and multi-scale feature aggregation to produce task-specific prediction at a high resolution. Our method achieves superior multi-task performance on NYUD-v2 and PASCAL-Context datasets respectively, and significantly outperforms previous state-of-the-arts. The code is available at https://github.com/prismformore/InvPT","url_abs":"https://arxiv.org/abs/2203.07997v3","url_pdf":"https://arxiv.org/pdf/2203.07997v3.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":"inverted-pyramid-multi-task-transformer-for","repo_url":"https://github.com/prismformore/InvPT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"boundary-detection","task_name":"Boundary Detection"},{"task_slug":"human-parsing","task_name":"Human Parsing"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"saliency-detection","task_name":"Saliency Detection"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"surface-normal-estimation","task_name":"Surface Normal Estimation"},{"task_slug":"surface-normals-estimation","task_name":"Surface Normals Estimation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/boundary-detection-on-nyu-depth-v2","task":"Boundary Detection","dataset":"NYU-Depth V2","model":"InvPT","rank_in_archive_order":1,"of":3,"metrics":{"odsF":"78.1"},"uses_additional_data":false},{"leaderboard":"/sota/boundary-detection-on-pascal-context","task":"Boundary Detection","dataset":"PASCAL Context","model":"InvPT","rank_in_archive_order":1,"of":1,"metrics":{"odsF":"73"},"uses_additional_data":false},{"leaderboard":"/sota/human-parsing-on-pascal-context","task":"Human Parsing","dataset":"PASCAL Context","model":"InvPT","rank_in_archive_order":1,"of":1,"metrics":{"mIoU":"67.61"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"InvPT","rank_in_archive_order":70,"of":85,"metrics":{"RMSE":"0.5183"},"uses_additional_data":false},{"leaderboard":"/sota/saliency-detection-on-pascal-context","task":"Saliency Detection","dataset":"PASCAL Context","model":"InvPT","rank_in_archive_order":1,"of":1,"metrics":{"max_F1":"84.81"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"InvPT","rank_in_archive_order":34,"of":121,"metrics":{"Mean IoU":"53.56%"},"uses_additional_data":false},{"leaderboard":"/sota/surface-normals-estimation-on-pascal-context","task":"Surface Normals Estimation","dataset":"PASCAL Context","model":"InvPT","rank_in_archive_order":1,"of":1,"metrics":{"Mean Angle Error":"14.15"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.07997","atlas_url":"https://app.syntology.ai/?focus=2203.07997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07997"}},"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":"deterministic:regex_extraction","url":"https://github.com/prismformore/InvPT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":"eda4c531e76e3fa8","entry":"normalize_tensor","repo":"prismformore/InvPT","repo_kind":"official","path":"InvPT/evaluation/eval_normals.py","file_url":"https://github.com/prismformore/InvPT/blob/HEAD/InvPT/evaluation/eval_normals.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eda4c531e76e3fa8"}},{"code_sha256_prefix":"098a8251265f82c2","entry":"uint82bin","repo":"prismformore/InvPT","repo_kind":"official","path":"InvPT/inference.py","file_url":"https://github.com/prismformore/InvPT/blob/HEAD/InvPT/inference.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":"098a8251265f82c2"}},{"code_sha256_prefix":"c4d6071bb0b87887","entry":"get_infer_transforms","repo":"prismformore/InvPT","repo_kind":"official","path":"InvPT/inference.py","file_url":"https://github.com/prismformore/InvPT/blob/HEAD/InvPT/inference.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":"c4d6071bb0b87887"}},{"code_sha256_prefix":"6a216e80da829b4d","entry":"get_single_task_meter","repo":"prismformore/InvPT","repo_kind":"official","path":"InvPT/evaluation/evaluate_utils.py","file_url":"https://github.com/prismformore/InvPT/blob/HEAD/InvPT/evaluation/evaluate_utils.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":"6a216e80da829b4d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}