{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/complexity-experts-are-task-discriminative","title":"Complexity Experts are Task-Discriminative Learners for Any Image Restoration","arxiv_id":"2411.18466","date":"2024-11-27","proceeding":"CVPR 2025 1","authors":["Eduard Zamfir","Zongwei Wu","Nancy Mehta","Yuedong Tan","Danda Pani Paudel","Yulun Zhang","Radu Timofte"],"abstract":"Recent advancements in all-in-one image restoration models have revolutionized the ability to address diverse degradations through a unified framework. However, parameters tied to specific tasks often remain inactive for other tasks, making mixture-of-experts (MoE) architectures a natural extension. Despite this, MoEs often show inconsistent behavior, with some experts unexpectedly generalizing across tasks while others struggle within their intended scope. This hinders leveraging MoEs' computational benefits by bypassing irrelevant experts during inference. We attribute this undesired behavior to the uniform and rigid architecture of traditional MoEs. To address this, we introduce ``complexity experts\" -- flexible expert blocks with varying computational complexity and receptive fields. A key challenge is assigning tasks to each expert, as degradation complexity is unknown in advance. Thus, we execute tasks with a simple bias toward lower complexity. To our surprise, this preference effectively drives task-specific allocation, assigning tasks to experts with the appropriate complexity. Extensive experiments validate our approach, demonstrating the ability to bypass irrelevant experts during inference while maintaining superior performance. The proposed MoCE-IR model outperforms state-of-the-art methods, affirming its efficiency and practical applicability. The source will be publicly made available at \\href{https://eduardzamfir.github.io/moceir/}{\\texttt{eduardzamfir.github.io/MoCE-IR/}}","url_abs":"https://arxiv.org/abs/2411.18466v1","url_pdf":"https://arxiv.org/pdf/2411.18466v1.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":[],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"blind-all-in-one-image-restoration","task_name":"Blind All-in-One Image Restoration"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/blind-all-in-one-image-restoration-on-3","task":"Blind All-in-One Image Restoration","dataset":"3-Degradations","model":"MoCE-IR","rank_in_archive_order":2,"of":9,"metrics":{"Average PSNR":"32.73","SSIM":"0.917"},"uses_additional_data":false},{"leaderboard":"/sota/blind-all-in-one-image-restoration-on-5","task":"Blind All-in-One Image Restoration","dataset":"5-Degradations","model":"MoCE-IR","rank_in_archive_order":2,"of":9,"metrics":{"Average PSNR":"30.58","SSIM":"0.919"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.18466","atlas_url":"https://app.syntology.ai/?focus=2411.18466","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2411.18466"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2411.18466\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2411.18466"},"call":"get_concepts_for_paper(arxiv_id=\"2411.18466\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"aedeaa58fe7679feb22bc2685c6d22bcc1c214c5e65e02a1aac355fc72379396","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}