{"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/blind-image-quality-assessment-via-vision","title":"Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective","arxiv_id":"2303.14968","date":"2023-03-27","proceeding":"CVPR 2023 1","authors":["Weixia Zhang","Guangtao Zhai","Ying WEI","Xiaokang Yang","Kede Ma"],"abstract":"We aim at advancing blind image quality assessment (BIQA), which predicts the human perception of image quality without any reference information. We develop a general and automated multitask learning scheme for BIQA to exploit auxiliary knowledge from other tasks, in a way that the model parameter sharing and the loss weighting are determined automatically. Specifically, we first describe all candidate label combinations (from multiple tasks) using a textual template, and compute the joint probability from the cosine similarities of the visual-textual embeddings. Predictions of each task can be inferred from the joint distribution, and optimized by carefully designed loss functions. Through comprehensive experiments on learning three tasks - BIQA, scene classification, and distortion type identification, we verify that the proposed BIQA method 1) benefits from the scene classification and distortion type identification tasks and outperforms the state-of-the-art on multiple IQA datasets, 2) is more robust in the group maximum differentiation competition, and 3) realigns the quality annotations from different IQA datasets more effectively. The source code is available at https://github.com/zwx8981/LIQE.","url_abs":"https://arxiv.org/abs/2303.14968v1","url_pdf":"https://arxiv.org/pdf/2303.14968v1.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":"blind-image-quality-assessment-via-vision","repo_url":"https://github.com/zwx8981/liqe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"no-reference-image-quality-assessment","task_name":"No-Reference Image Quality Assessment"},{"task_slug":"scene-classification","task_name":"Scene Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.14968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14968"}},"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/zwx8981/liqe","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/zwx8981/LIQE","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"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":"83eaf2b87256e5c9","entry":"detach_to_numpy","repo":"zwx8981/LIQE","repo_kind":"official","path":"weight_methods.py","file_url":"https://github.com/zwx8981/LIQE/blob/HEAD/weight_methods.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":"83eaf2b87256e5c9"}},{"code_sha256_prefix":"1d7c68b369e70ab0","entry":"has_file_allowed_extension","repo":"zwx8981/LIQE","repo_kind":"official","path":"ImageDataset.py","file_url":"https://github.com/zwx8981/LIQE/blob/HEAD/ImageDataset.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":"1d7c68b369e70ab0"}},{"code_sha256_prefix":"86518d14632a4d35","entry":"image_loader","repo":"zwx8981/LIQE","repo_kind":"official","path":"ImageDataset.py","file_url":"https://github.com/zwx8981/LIQE/blob/HEAD/ImageDataset.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":"86518d14632a4d35"}},{"code_sha256_prefix":"eecc2b52c51e67dc","entry":"logistic_func","repo":"zwx8981/LIQE","repo_kind":"official","path":"BIQA_benchmark.py","file_url":"https://github.com/zwx8981/LIQE/blob/HEAD/BIQA_benchmark.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":"eecc2b52c51e67dc"}},{"code_sha256_prefix":"cd659f3fd89ca41e","entry":"loss_m3","repo":"zwx8981/LIQE","repo_kind":"official","path":"MNL_Loss.py","file_url":"https://github.com/zwx8981/LIQE/blob/HEAD/MNL_Loss.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":"cd659f3fd89ca41e"}},{"code_sha256_prefix":"ff0821a6182abda4","entry":"do_batch","repo":"zwx8981/LIQE","repo_kind":"official","path":"train_liqe_single.py","file_url":"https://github.com/zwx8981/LIQE/blob/HEAD/train_liqe_single.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":"ff0821a6182abda4"}},{"code_sha256_prefix":"63ac8d70c8975857","entry":"loss_m","repo":"zwx8981/LIQE","repo_kind":"official","path":"MNL_Loss.py","file_url":"https://github.com/zwx8981/LIQE/blob/HEAD/MNL_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":"63ac8d70c8975857"}},{"code_sha256_prefix":"e34fa4a19a9e0622","entry":"loss_m2","repo":"zwx8981/LIQE","repo_kind":"official","path":"MNL_Loss.py","file_url":"https://github.com/zwx8981/LIQE/blob/HEAD/MNL_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":"e34fa4a19a9e0622"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}