{"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/cola-conditional-dropout-and-language-driven","title":"CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection","arxiv_id":"2407.06780","date":"2024-07-09","proceeding":null,"authors":["Shuang Hao","Chunlin Zhong","He Tang"],"abstract":"The depth/thermal information is beneficial for detecting salient object with conventional RGB images. However, in dual-modal salient object detection (SOD) model, the robustness against noisy inputs and modality missing is crucial but rarely studied. To tackle this problem, we introduce \\textbf{Co}nditional Dropout and \\textbf{LA}nguage-driven(\\textbf{CoLA}) framework comprising two core components. 1) Language-driven Quality Assessment (LQA): Leveraging a pretrained vision-language model with a prompt learner, the LQA recalibrates image contributions without requiring additional quality annotations. This approach effectively mitigates the impact of noisy inputs. 2) Conditional Dropout (CD): A learning method to strengthen the model's adaptability in scenarios with missing modalities, while preserving its performance under complete modalities. The CD serves as a plug-in training scheme that treats modality-missing as conditions, strengthening the overall robustness of various dual-modal SOD models. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art dual-modal SOD models, under both modality-complete and modality-missing conditions. We will release source code upon acceptance.","url_abs":"https://arxiv.org/abs/2407.06780v1","url_pdf":"https://arxiv.org/pdf/2407.06780v1.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":"cola-conditional-dropout-and-language-driven","repo_url":"https://github.com/ssecv/CoLA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"CoLA"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"salient-object-detection","task_name":"RGB Salient Object Detection"},{"task_slug":"rgb-d-salient-object-detection","task_name":"RGB-D Salient Object Detection"},{"task_slug":"rgb-t-salient-object-detection","task_name":"RGB-T Salient Object Detection"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/rgb-d-salient-object-detection-on-des","task":"RGB-D Salient Object Detection","dataset":"DES","model":"CoLANet","rank_in_archive_order":7,"of":13,"metrics":{"Average MAE":"0.018","S-Measure":"93.5","max E-Measure":"96.3","max F-Measure":"92.5"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nju2k","task":"RGB-D Salient Object Detection","dataset":"NJU2K","model":"CoLANet","rank_in_archive_order":2,"of":27,"metrics":{"Average MAE":"0.029","S-Measure":"93.4","max E-Measure":"94.7","max F-Measure":"91.3"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nlpr","task":"RGB-D Salient Object Detection","dataset":"NLPR","model":"CoLANet","rank_in_archive_order":2,"of":14,"metrics":{"Average MAE":"0.021","S-Measure":"93.5","max E-Measure":"95.7","max F-Measure":"90.9"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-sip","task":"RGB-D Salient Object Detection","dataset":"SIP","model":"CoLANet","rank_in_archive_order":4,"of":16,"metrics":{"Average MAE":"0.042","S-Measure":"89.5","max E-Measure":"93.5","max F-Measure":"89.4"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-stere","task":"RGB-D Salient Object Detection","dataset":"STERE","model":"CoLANet","rank_in_archive_order":5,"of":14,"metrics":{"Average MAE":"0.039","S-Measure":"90.8","max E-Measure":"94.1","max F-Measure":"88.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.06780","atlas_url":"https://app.syntology.ai/?focus=2407.06780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06780"}},"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/ssecv/CoLA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":5,"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"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":"98f385d847636a3e","entry":"basic_clean","repo":"ssecv/CoLA","repo_kind":"official","path":"code/pytorch/clip/simple_tokenizer.py","file_url":"https://github.com/ssecv/CoLA/blob/HEAD/code/pytorch/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"ssecv/CoLA","repo_kind":"official","path":"code/MindSpore/Net.py","file_url":"https://github.com/ssecv/CoLA/blob/HEAD/code/MindSpore/Net.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":"f1885b1dcacdbbfa","entry":"convblock","repo":"ssecv/CoLA","repo_kind":"official","path":"code/MindSpore/Net.py","file_url":"https://github.com/ssecv/CoLA/blob/HEAD/code/MindSpore/Net.py","link_basis":"first_harvest_node","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":"f1885b1dcacdbbfa"}},{"code_sha256_prefix":"c5900dcd35b2d0a3","entry":"cv_random_flip","repo":"ssecv/CoLA","repo_kind":"official","path":"code/MindSpore/data.py","file_url":"https://github.com/ssecv/CoLA/blob/HEAD/code/MindSpore/data.py","link_basis":"first_harvest_node","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":"d919ae32e5e4e616","entry":"get_pairs","repo":"ssecv/CoLA","repo_kind":"official","path":"code/pytorch/clip/simple_tokenizer.py","file_url":"https://github.com/ssecv/CoLA/blob/HEAD/code/pytorch/clip/simple_tokenizer.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":"d919ae32e5e4e616"}},{"code_sha256_prefix":"7edae4532113d306","entry":"randomCrop","repo":"ssecv/CoLA","repo_kind":"official","path":"code/MindSpore/data.py","file_url":"https://github.com/ssecv/CoLA/blob/HEAD/code/MindSpore/data.py","link_basis":"first_harvest_node","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":"9542161e9640b858","entry":"whitespace_clean","repo":"ssecv/CoLA","repo_kind":"official","path":"code/pytorch/clip/simple_tokenizer.py","file_url":"https://github.com/ssecv/CoLA/blob/HEAD/code/pytorch/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"129b804760b3115f","entry":"zero_module","repo":"ssecv/CoLA","repo_kind":"official","path":"code/MindSpore/Net.py","file_url":"https://github.com/ssecv/CoLA/blob/HEAD/code/MindSpore/Net.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":"129b804760b3115f"}},{"code_sha256_prefix":"39e6b23b55f376ea","entry":"build_model","repo":"ssecv/CoLA","repo_kind":"official","path":"code/pytorch/clip/model.py","file_url":"https://github.com/ssecv/CoLA/blob/HEAD/code/pytorch/clip/model.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":"39e6b23b55f376ea"}},{"code_sha256_prefix":"f6f30e41636ae569","entry":"load","repo":"ssecv/CoLA","repo_kind":"official","path":"code/pytorch/clip/clip.py","file_url":"https://github.com/ssecv/CoLA/blob/HEAD/code/pytorch/clip/clip.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":"f6f30e41636ae569"}},{"code_sha256_prefix":"2ce2ebcbdb96d573","entry":"randomRotation","repo":"ssecv/CoLA","repo_kind":"official","path":"code/MindSpore/data.py","file_url":"https://github.com/ssecv/CoLA/blob/HEAD/code/MindSpore/data.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":"2ce2ebcbdb96d573"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}