{"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/promoting-saliency-from-depth-deep-1","title":"Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection","arxiv_id":"2205.07179","date":"2022-05-15","proceeding":"ICLR 2022 4","authors":["Wei Ji","Jingjing Li","Qi Bi","Chuan Guo","Jie Liu","Li Cheng"],"abstract":"Growing interests in RGB-D salient object detection (RGB-D SOD) have been witnessed in recent years, owing partly to the popularity of depth sensors and the rapid progress of deep learning techniques. Unfortunately, existing RGB-D SOD methods typically demand large quantity of training images being thoroughly annotated at pixel-level. The laborious and time-consuming manual annotation has become a real bottleneck in various practical scenarios. On the other hand, current unsupervised RGB-D SOD methods still heavily rely on handcrafted feature representations. This inspires us to propose in this paper a deep unsupervised RGB-D saliency detection approach, which requires no manual pixel-level annotation during training. It is realized by two key ingredients in our training pipeline. First, a depth-disentangled saliency update (DSU) framework is designed to automatically produce pseudo-labels with iterative follow-up refinements, which provides more trustworthy supervision signals for training the saliency network. Second, an attentive training strategy is introduced to tackle the issue of noisy pseudo-labels, by properly re-weighting to highlight the more reliable pseudo-labels. Extensive experiments demonstrate the superior efficiency and effectiveness of our approach in tackling the challenging unsupervised RGB-D SOD scenarios. Moreover, our approach can also be adapted to work in fully-supervised situation. Empirical studies show the incorporation of our approach gives rise to notably performance improvement in existing supervised RGB-D SOD models.","url_abs":"https://arxiv.org/abs/2205.07179v1","url_pdf":"https://arxiv.org/pdf/2205.07179v1.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":"promoting-saliency-from-depth-deep-1","repo_url":"https://github.com/jiwei0921/dsu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"rgb-d-salient-object-detection","task_name":"RGB-D Salient Object Detection"},{"task_slug":"saliency-detection","task_name":"Saliency 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":"https://syntology.ai/paper/2205.07179","atlas_url":"https://app.syntology.ai/?focus=2205.07179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.07179"}},"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/jiwei0921/dsu","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":3,"ran_honours":1,"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":6,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"jiwei0921/dsu","repo_kind":"official","path":"DSU_Code/model/ResNet.py","file_url":"https://github.com/jiwei0921/dsu/blob/HEAD/DSU_Code/model/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":"fac5364e2f53c6db"}},{"code_sha256_prefix":"c5900dcd35b2d0a3","entry":"cv_random_flip","repo":"jiwei0921/dsu","repo_kind":"official","path":"DSU_Code/data.py","file_url":"https://github.com/jiwei0921/dsu/blob/HEAD/DSU_Code/data.py","link_basis":"harvester_set","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":"c5900dcd35b2d0a3"}},{"code_sha256_prefix":"d6d03dafd950d6c4","entry":"gkern","repo":"jiwei0921/dsu","repo_kind":"official","path":"DSU_Code/model/HolisticAttention.py","file_url":"https://github.com/jiwei0921/dsu/blob/HEAD/DSU_Code/model/HolisticAttention.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":"d6d03dafd950d6c4"}},{"code_sha256_prefix":"caa39751253d7993","entry":"loss_weight","repo":"jiwei0921/dsu","repo_kind":"official","path":"DSU_Code/attentive_training.py","file_url":"https://github.com/jiwei0921/dsu/blob/HEAD/DSU_Code/attentive_training.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":"caa39751253d7993"}},{"code_sha256_prefix":"f11714f9833718d2","entry":"min_max_norm","repo":"jiwei0921/dsu","repo_kind":"official","path":"DSU_Code/model/HolisticAttention.py","file_url":"https://github.com/jiwei0921/dsu/blob/HEAD/DSU_Code/model/HolisticAttention.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f11714f9833718d2"}},{"code_sha256_prefix":"7edae4532113d306","entry":"randomCrop","repo":"jiwei0921/dsu","repo_kind":"official","path":"DSU_Code/data.py","file_url":"https://github.com/jiwei0921/dsu/blob/HEAD/DSU_Code/data.py","link_basis":"harvester_set","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":"7edae4532113d306"}},{"code_sha256_prefix":"c895d03e6df7cb22","entry":"iou","repo":"jiwei0921/dsu","repo_kind":"official","path":"DSU_Code/utils.py","file_url":"https://github.com/jiwei0921/dsu/blob/HEAD/DSU_Code/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":"c895d03e6df7cb22"}},{"code_sha256_prefix":"2ce2ebcbdb96d573","entry":"randomRotation","repo":"jiwei0921/dsu","repo_kind":"official","path":"DSU_Code/data.py","file_url":"https://github.com/jiwei0921/dsu/blob/HEAD/DSU_Code/data.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":"2ce2ebcbdb96d573"}},{"code_sha256_prefix":"614514b055d1b97b","entry":"update_pseudoLabel","repo":"jiwei0921/dsu","repo_kind":"official","path":"DSU_Code/attentive_training.py","file_url":"https://github.com/jiwei0921/dsu/blob/HEAD/DSU_Code/attentive_training.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":"614514b055d1b97b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}