{"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/fast-and-memory-efficient-network-towards","title":"Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution","arxiv_id":"2204.08397","date":"2022-04-18","proceeding":null,"authors":["Zongcai Du","Ding Liu","Jie Liu","Jie Tang","Gangshan Wu","Lean Fu"],"abstract":"Runtime and memory consumption are two important aspects for efficient image super-resolution (EISR) models to be deployed on resource-constrained devices. Recent advances in EISR exploit distillation and aggregation strategies with plenty of channel split and concatenation operations to make full use of limited hierarchical features. In contrast, sequential network operations avoid frequently accessing preceding states and extra nodes, and thus are beneficial to reducing the memory consumption and runtime overhead. Following this idea, we design our lightweight network backbone by mainly stacking multiple highly optimized convolution and activation layers and decreasing the usage of feature fusion. We propose a novel sequential attention branch, where every pixel is assigned an important factor according to local and global contexts, to enhance high-frequency details. In addition, we tailor the residual block for EISR and propose an enhanced residual block (ERB) to further accelerate the network inference. Finally, combining all the above techniques, we construct a fast and memory-efficient network (FMEN) and its small version FMEN-S, which runs 33% faster and reduces 74% memory consumption compared with the state-of-the-art EISR model: E-RFDN, the champion in AIM 2020 efficient super-resolution challenge. Besides, FMEN-S achieves the lowest memory consumption and the second shortest runtime in NTIRE 2022 challenge on efficient super-resolution. Code is available at https://github.com/NJU-Jet/FMEN.","url_abs":"https://arxiv.org/abs/2204.08397v1","url_pdf":"https://arxiv.org/pdf/2204.08397v1.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":"fast-and-memory-efficient-network-towards","repo_url":"https://github.com/nju-jet/fmen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fast-and-memory-efficient-network-towards","repo_url":"https://github.com/Gaurav14cs17/Reparameterization-Denoising","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.08397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08397"}},"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/Gaurav14cs17/Reparameterization-Denoising","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nju-jet/fmen","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":2,"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":1},"listed":{"samples":4,"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":"de2d5ef7779696d7","entry":"get_bn_bias","repo":"nju-jet/fmen","repo_kind":"official","path":"train_fmen.py","file_url":"https://github.com/nju-jet/fmen/blob/HEAD/train_fmen.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"de2d5ef7779696d7"}},{"code_sha256_prefix":"2d54a0eddac3a07c","entry":"make_model","repo":"nju-jet/fmen","repo_kind":"official","path":"train_fmen.py","file_url":"https://github.com/nju-jet/fmen/blob/HEAD/train_fmen.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2d54a0eddac3a07c"}},{"code_sha256_prefix":"e8a639b8136a44be","entry":"make_model","repo":"nju-jet/fmen","repo_kind":"official","path":"test_fmen.py","file_url":"https://github.com/nju-jet/fmen/blob/HEAD/test_fmen.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e8a639b8136a44be"}},{"code_sha256_prefix":"36de767510d9fb56","entry":"pad_tensor","repo":"nju-jet/fmen","repo_kind":"official","path":"train_fmen.py","file_url":"https://github.com/nju-jet/fmen/blob/HEAD/train_fmen.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"36de767510d9fb56"}},{"code_sha256_prefix":"8fcd86b3d0e435c6","entry":"data_augmentation","repo":"Gaurav14cs17/Reparameterization-Denoising","repo_kind":"listed","path":"utils/utils.py","file_url":"https://github.com/Gaurav14cs17/Reparameterization-Denoising/blob/HEAD/utils/utils.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":"8fcd86b3d0e435c6"}},{"code_sha256_prefix":"e1fc3727aabb3df4","entry":"dwt_init","repo":"Gaurav14cs17/Reparameterization-Denoising","repo_kind":"listed","path":"models/MFDNet.py","file_url":"https://github.com/Gaurav14cs17/Reparameterization-Denoising/blob/HEAD/models/MFDNet.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":"e1fc3727aabb3df4"}},{"code_sha256_prefix":"90b385706ca5a05c","entry":"iwt_init","repo":"Gaurav14cs17/Reparameterization-Denoising","repo_kind":"listed","path":"models/MFDNet.py","file_url":"https://github.com/Gaurav14cs17/Reparameterization-Denoising/blob/HEAD/models/MFDNet.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":"90b385706ca5a05c"}},{"code_sha256_prefix":"d37bd3a531577371","entry":"load_model","repo":"Gaurav14cs17/Reparameterization-Denoising","repo_kind":"listed","path":"models/MFDNet.py","file_url":"https://github.com/Gaurav14cs17/Reparameterization-Denoising/blob/HEAD/models/MFDNet.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":"d37bd3a531577371"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}