{"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/frequency-adaptive-dilated-convolution-for","title":"Frequency-Adaptive Dilated Convolution for Semantic Segmentation","arxiv_id":"2403.05369","date":"2024-03-08","proceeding":"CVPR 2024 1","authors":["Linwei Chen","Lin Gu","Ying Fu"],"abstract":"Dilated convolution, which expands the receptive field by inserting gaps between its consecutive elements, is widely employed in computer vision. In this study, we propose three strategies to improve individual phases of dilated convolution from the view of spectrum analysis. Departing from the conventional practice of fixing a global dilation rate as a hyperparameter, we introduce Frequency-Adaptive Dilated Convolution (FADC), which dynamically adjusts dilation rates spatially based on local frequency components. Subsequently, we design two plug-in modules to directly enhance effective bandwidth and receptive field size. The Adaptive Kernel (AdaKern) module decomposes convolution weights into low-frequency and high-frequency components, dynamically adjusting the ratio between these components on a per-channel basis. By increasing the high-frequency part of convolution weights, AdaKern captures more high-frequency components, thereby improving effective bandwidth. The Frequency Selection (FreqSelect) module optimally balances high- and low-frequency components in feature representations through spatially variant reweighting. It suppresses high frequencies in the background to encourage FADC to learn a larger dilation, thereby increasing the receptive field for an expanded scope. Extensive experiments on segmentation and object detection consistently validate the efficacy of our approach. The code is publicly available at https://github.com/Linwei-Chen/FADC.","url_abs":"https://arxiv.org/abs/2403.05369v6","url_pdf":"https://arxiv.org/pdf/2403.05369v6.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":"frequency-adaptive-dilated-convolution-for","repo_url":"https://github.com/linwei-chen/fadc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.05369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05369"}},"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":"deterministic:regex_extraction","url":"https://github.com/ying-fu/FADC","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5},"by_repo_kind":{"found_in_text":{"samples":5,"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":"2baf2f5ca3ea1a66","entry":"generate_laplacian_pyramid","repo":"ying-fu/FADC","repo_kind":"found_in_text","path":"models/conv_custom.py","file_url":"https://github.com/ying-fu/FADC/blob/HEAD/models/conv_custom.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2baf2f5ca3ea1a66"}},{"code_sha256_prefix":"c7f5b588454ed76a","entry":"get_dwconv","repo":"ying-fu/FADC","repo_kind":"found_in_text","path":"mmcv_custom/gn_module.py","file_url":"https://github.com/ying-fu/FADC/blob/HEAD/mmcv_custom/gn_module.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c7f5b588454ed76a"}},{"code_sha256_prefix":"38ab0f5789bdec42","entry":"get_dwconv","repo":"ying-fu/FADC","repo_kind":"found_in_text","path":"decode_heads/uper_head_gnconv.py","file_url":"https://github.com/ying-fu/FADC/blob/HEAD/decode_heads/uper_head_gnconv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"38ab0f5789bdec42"}},{"code_sha256_prefix":"ac7655e965b76118","entry":"get_num_layer_layer_wise","repo":"ying-fu/FADC","repo_kind":"found_in_text","path":"mmcv_custom/layer_decay_optimizer_constructor.py","file_url":"https://github.com/ying-fu/FADC/blob/HEAD/mmcv_custom/layer_decay_optimizer_constructor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ac7655e965b76118"}},{"code_sha256_prefix":"be134d6ef63b5192","entry":"get_num_layer_stage_wise","repo":"ying-fu/FADC","repo_kind":"found_in_text","path":"mmcv_custom/layer_decay_optimizer_constructor.py","file_url":"https://github.com/ying-fu/FADC/blob/HEAD/mmcv_custom/layer_decay_optimizer_constructor.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"be134d6ef63b5192"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}