{"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/joint-learning-of-salient-object-detection","title":"Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction","arxiv_id":"2203.04895","date":"2022-03-09","proceeding":null,"authors":["Xiaoqi Zhao","Youwei Pang","Lihe Zhang","Huchuan Lu"],"abstract":"Benefiting from color independence, illumination invariance and location discrimination attributed by the depth map, it can provide important supplemental information for extracting salient objects in complex environments. However, high-quality depth sensors are expensive and can not be widely applied. While general depth sensors produce the noisy and sparse depth information, which brings the depth-based networks with irreversible interference. In this paper, we propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD). Specifically, we unify three complementary tasks: depth estimation, salient object detection and contour estimation. The multi-task mechanism promotes the model to learn the task-aware features from the auxiliary tasks. In this way, the depth information can be completed and purified. Moreover, we introduce a multi-modal filtered transformer (MFT) module, which equips with three modality-specific filters to generate the transformer-enhanced feature for each modality. The proposed model works in a depth-free style during the testing phase. Experiments show that it not only significantly surpasses the depth-based RGB-D SOD methods on multiple datasets, but also precisely predicts a high-quality depth map and salient contour at the same time. And, the resulted depth map can help existing RGB-D SOD methods obtain significant performance gain. The source code will be publicly available at https://github.com/Xiaoqi-Zhao-DLUT/MMFT.","url_abs":"https://arxiv.org/abs/2203.04895v2","url_pdf":"https://arxiv.org/pdf/2203.04895v2.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":"joint-learning-of-salient-object-detection","repo_url":"https://github.com/xiaoqi-zhao-dlut/mmft","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"rgb-d-salient-object-detection","task_name":"RGB-D Salient Object Detection"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2203.04895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04895"}},"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/xiaoqi-zhao-dlut/mmft","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":3,"unverified":8},"by_repo_kind":{"official":{"samples":11,"ran":3,"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":"6154e3744ece5728","entry":"create_window","repo":"xiaoqi-zhao-dlut/mmft","repo_kind":"official","path":"model/ssim_loss.py","file_url":"https://github.com/xiaoqi-zhao-dlut/mmft/blob/HEAD/model/ssim_loss.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6154e3744ece5728"}},{"code_sha256_prefix":"c56b7ef16f309a45","entry":"gaussian","repo":"xiaoqi-zhao-dlut/mmft","repo_kind":"official","path":"model/ssim_loss.py","file_url":"https://github.com/xiaoqi-zhao-dlut/mmft/blob/HEAD/model/ssim_loss.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c56b7ef16f309a45"}},{"code_sha256_prefix":"c23b05634625d281","entry":"l2_regularisation","repo":"xiaoqi-zhao-dlut/mmft","repo_kind":"official","path":"utils.py","file_url":"https://github.com/xiaoqi-zhao-dlut/mmft/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c23b05634625d281"}},{"code_sha256_prefix":"1f66fcae571ac878","entry":"cv_random_flip","repo":"xiaoqi-zhao-dlut/mmft","repo_kind":"official","path":"data_depth_free_multi_task.py","file_url":"https://github.com/xiaoqi-zhao-dlut/mmft/blob/HEAD/data_depth_free_multi_task.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":"1f66fcae571ac878"}},{"code_sha256_prefix":"7616d055c901e967","entry":"get_log_kernel2d_pt","repo":"xiaoqi-zhao-dlut/mmft","repo_kind":"official","path":"depth_bokeh.py","file_url":"https://github.com/xiaoqi-zhao-dlut/mmft/blob/HEAD/depth_bokeh.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":"7616d055c901e967"}},{"code_sha256_prefix":"8ac93407f634dcc8","entry":"randomCrop","repo":"xiaoqi-zhao-dlut/mmft","repo_kind":"official","path":"data_depth_free_multi_task.py","file_url":"https://github.com/xiaoqi-zhao-dlut/mmft/blob/HEAD/data_depth_free_multi_task.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":"8ac93407f634dcc8"}},{"code_sha256_prefix":"bbfbb005e8b57cb0","entry":"randomRotation","repo":"xiaoqi-zhao-dlut/mmft","repo_kind":"official","path":"data_depth_free_multi_task.py","file_url":"https://github.com/xiaoqi-zhao-dlut/mmft/blob/HEAD/data_depth_free_multi_task.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":"bbfbb005e8b57cb0"}},{"code_sha256_prefix":"2c02b53e0dbd4404","entry":"rmse_linear","repo":"xiaoqi-zhao-dlut/mmft","repo_kind":"official","path":"Depth_eva.py","file_url":"https://github.com/xiaoqi-zhao-dlut/mmft/blob/HEAD/Depth_eva.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":"2c02b53e0dbd4404"}},{"code_sha256_prefix":"848e15a6cdbcecff","entry":"rmse_log","repo":"xiaoqi-zhao-dlut/mmft","repo_kind":"official","path":"Depth_eva.py","file_url":"https://github.com/xiaoqi-zhao-dlut/mmft/blob/HEAD/Depth_eva.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":"848e15a6cdbcecff"}},{"code_sha256_prefix":"9151c793f90473f0","entry":"ssim","repo":"xiaoqi-zhao-dlut/mmft","repo_kind":"official","path":"model/ssim_loss.py","file_url":"https://github.com/xiaoqi-zhao-dlut/mmft/blob/HEAD/model/ssim_loss.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":"9151c793f90473f0"}},{"code_sha256_prefix":"de2031d8d8e58197","entry":"threeshold_percentage","repo":"xiaoqi-zhao-dlut/mmft","repo_kind":"official","path":"Depth_eva.py","file_url":"https://github.com/xiaoqi-zhao-dlut/mmft/blob/HEAD/Depth_eva.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":"de2031d8d8e58197"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}