{"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/re-iqa-unsupervised-learning-for-image","title":"Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild","arxiv_id":"2304.00451","date":"2023-04-02","proceeding":"CVPR 2023 1","authors":["Avinab Saha","Sandeep Mishra","Alan C. Bovik"],"abstract":"Automatic Perceptual Image Quality Assessment is a challenging problem that impacts billions of internet, and social media users daily. To advance research in this field, we propose a Mixture of Experts approach to train two separate encoders to learn high-level content and low-level image quality features in an unsupervised setting. The unique novelty of our approach is its ability to generate low-level representations of image quality that are complementary to high-level features representing image content. We refer to the framework used to train the two encoders as Re-IQA. For Image Quality Assessment in the Wild, we deploy the complementary low and high-level image representations obtained from the Re-IQA framework to train a linear regression model, which is used to map the image representations to the ground truth quality scores, refer Figure 1. Our method achieves state-of-the-art performance on multiple large-scale image quality assessment databases containing both real and synthetic distortions, demonstrating how deep neural networks can be trained in an unsupervised setting to produce perceptually relevant representations. We conclude from our experiments that the low and high-level features obtained are indeed complementary and positively impact the performance of the linear regressor. A public release of all the codes associated with this work will be made available on GitHub.","url_abs":"https://arxiv.org/abs/2304.00451v2","url_pdf":"https://arxiv.org/pdf/2304.00451v2.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":"re-iqa-unsupervised-learning-for-image","repo_url":"https://github.com/avinabsaha/ReIQA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"re-iqa-unsupervised-learning-for-image","repo_url":"https://github.com/miccunifi/arniqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"no-reference-image-quality-assessment","task_name":"No-Reference Image Quality Assessment"}],"methods":[{"method_slug":"linear-regression","method_name":"Linear Regression"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/no-reference-image-quality-assessment-on-csiq","task":"No-Reference Image Quality Assessment","dataset":"CSIQ","model":"Re-IQA","rank_in_archive_order":3,"of":8,"metrics":{"PLCC":"0.960","SRCC":"0.947"},"uses_additional_data":false},{"leaderboard":"/sota/no-reference-image-quality-assessment-on-1","task":"No-Reference Image Quality Assessment","dataset":"KADID-10k","model":"Re-IQA","rank_in_archive_order":5,"of":9,"metrics":{"PLCC":"0.885","SRCC":"0.872"},"uses_additional_data":false},{"leaderboard":"/sota/no-reference-image-quality-assessment-on","task":"No-Reference Image Quality Assessment","dataset":"TID2013","model":"Re-IQA","rank_in_archive_order":7,"of":8,"metrics":{"PLCC":"0.861","SRCC":"0.804"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.00451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.00451"}},"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/avinabsaha/ReIQA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/miccunifi/arniqa","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":"f7954d813ff42b0f","entry":"MoCo","repo":"avinabsaha/ReIQA","repo_kind":"official","path":"moco/builder.py","file_url":"https://github.com/avinabsaha/ReIQA/blob/HEAD/moco/builder.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":"f7954d813ff42b0f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}