{"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/fade-fusing-the-assets-of-decoder-and-encoder","title":"FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling","arxiv_id":"2207.10392","date":"2022-07-21","proceeding":null,"authors":["Hao Lu","Wenze Liu","Hongtao Fu","Zhiguo Cao"],"abstract":"We consider the problem of task-agnostic feature upsampling in dense prediction where an upsampling operator is required to facilitate both region-sensitive tasks like semantic segmentation and detail-sensitive tasks such as image matting. Existing upsampling operators often can work well in either type of the tasks, but not both. In this work, we present FADE, a novel, plug-and-play, and task-agnostic upsampling operator. FADE benefits from three design choices: i) considering encoder and decoder features jointly in upsampling kernel generation; ii) an efficient semi-shift convolutional operator that enables granular control over how each feature point contributes to upsampling kernels; iii) a decoder-dependent gating mechanism for enhanced detail delineation. We first study the upsampling properties of FADE on toy data and then evaluate it on large-scale semantic segmentation and image matting. In particular, FADE reveals its effectiveness and task-agnostic characteristic by consistently outperforming recent dynamic upsampling operators in different tasks. It also generalizes well across convolutional and transformer architectures with little computational overhead. Our work additionally provides thoughtful insights on what makes for task-agnostic upsampling. Code is available at: http://lnkiy.in/fade_in","url_abs":"https://arxiv.org/abs/2207.10392v2","url_pdf":"https://arxiv.org/pdf/2207.10392v2.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":"fade-fusing-the-assets-of-decoder-and-encoder","repo_url":"https://github.com/poppinace/fade","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"feature-upsampling","task_name":"Feature Upsampling"},{"task_slug":"image-matting","task_name":"Image Matting"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.10392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10392"}},"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/poppinace/fade","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"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":"3463cadcbdaba858","entry":"pred","repo":"poppinace/fade","repo_kind":"listed","path":"a2u_matting/resnet.py","file_url":"https://github.com/poppinace/fade/blob/HEAD/a2u_matting/resnet.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":"3463cadcbdaba858"}},{"code_sha256_prefix":"36549094a6bf992a","entry":"space_reassemble","repo":"poppinace/fade","repo_kind":"listed","path":"FADE_H2L.py","file_url":"https://github.com/poppinace/fade/blob/HEAD/FADE_H2L.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":"36549094a6bf992a"}},{"code_sha256_prefix":"7b6abef254c852d1","entry":"try_index","repo":"poppinace/fade","repo_kind":"listed","path":"a2u_matting/resnet.py","file_url":"https://github.com/poppinace/fade/blob/HEAD/a2u_matting/resnet.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":"7b6abef254c852d1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}