{"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":"/method/selective-kernel","slug":"selective-kernel","name":"Selective Kernel","full_name":"Selective Kernel","full_name_withheld":false,"description_markdown":"A **Selective Kernel** unit is a bottleneck block consisting of a sequence of 1×1 [convolution](https://paperswithcode.com/method/convolution), SK convolution and 1×1 convolution. It was proposed as part of the [SKNet](https://paperswithcode.com/method/sknet) CNN architecture. In general, all the large kernel convolutions in the original bottleneck blocks in [ResNeXt](https://paperswithcode.com/method/resnext) are replaced by the proposed SK convolutions, enabling the network to choose appropriate receptive field sizes in an adaptive manner. \r\n\r\nIn SK units, there are three important hyper-parameters which determine the final settings of SK convolutions: the number of paths $M$ that determines the number of choices of different kernels to be aggregated, the group number $G$ that controls the cardinality of each path, and the reduction ratio $r$ that controls the number of parameters in the fuse operator. One typical setting of SK convolutions is $\\text{SK}\\left[M, G, r\\right]$ to be $\\text{SK}\\left[2, 32, 16\\right]$.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Selective Kernel Networks","paper":"/paper/selective-kernel-networks","first_author":"Xiang Li","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/selective-kernel-networks"},"source":{"url":"http://arxiv.org/abs/1903.06586v2","title":"Selective Kernel Networks","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/osmr/imgclsmob/blob/68335927ba27f2356093b985bada0bc3989836b1/pytorch/pytorchcv/models/sknet.py#L15","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Skip Connection Blocks","url":"/methods/category/skip-connection-blocks","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Model Blocks","url":"/methods/category/image-model-blocks","pwc_aliases":[]}],"n_papers_tagged":27,"archive_num_papers":27,"papers_newest_first":[{"paper":"/paper/obiformer-a-fast-attentive-denoising","slug":"obiformer-a-fast-attentive-denoising","title":"OBIFormer: A Fast Attentive Denoising Framework for Oracle Bone Inscriptions","date":"2025-04-18","arxiv_id":"2504.13524","n_code_links":1,"syntology":null},{"paper":null,"slug":"slam-in-the-dark-self-supervised-learning-of","title":"SLAM in the Dark: Self-Supervised Learning of Pose, Depth and Loop-Closure from Thermal Images","date":"2025-02-26","arxiv_id":"2502.18932","n_code_links":0,"syntology":null},{"paper":"/paper/groklst-towards-high-resolution-benchmark-and","slug":"groklst-towards-high-resolution-benchmark-and","title":"MoCoLSK: Modality Conditioned High-Resolution Downscaling for Land Surface Temperature","date":"2024-09-30","arxiv_id":"2409.19835","n_code_links":1,"syntology":null},{"paper":null,"slug":"attention-guided-multi-scale-interaction","title":"Attention-Guided Multi-scale Interaction Network for Face Super-Resolution","date":"2024-09-01","arxiv_id":"2409.00591","n_code_links":0,"syntology":null},{"paper":"/paper/pick-or-mix-dynamic-channel-sampling-for-1","slug":"pick-or-mix-dynamic-channel-sampling-for-1","title":"Pick-or-Mix: Dynamic Channel Sampling for ConvNets","date":"2024-06-16","arxiv_id":"2406.10935","n_code_links":1,"syntology":null},{"paper":null,"slug":"lsksanet-a-novel-architecture-for-remote","title":"LSKSANet: A Novel Architecture for Remote Sensing Image Semantic Segmentation Leveraging Large Selective Kernel and Sparse Attention Mechanism","date":"2024-06-03","arxiv_id":"2406.01228","n_code_links":0,"syntology":null},{"paper":null,"slug":"mamballie-implicit-retinex-aware-low-light","title":"MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space","date":"2024-05-25","arxiv_id":"2405.16105","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-click-through-rate-prediction-method-based","title":"A Click-Through Rate Prediction Method Based on Cross-Importance of Multi-Order Features","date":"2024-05-14","arxiv_id":"2405.08852","n_code_links":0,"syntology":null},{"paper":"/paper/ac-mambaseg-an-adaptive-convolution-and-mamba","slug":"ac-mambaseg-an-adaptive-convolution-and-mamba","title":"AC-MAMBASEG: An adaptive convolution and Mamba-based architecture for enhanced skin lesion segmentation","date":"2024-05-05","arxiv_id":"2405.03011","n_code_links":1,"syntology":null},{"paper":"/paper/lsknet-a-foundation-lightweight-backbone-for","slug":"lsknet-a-foundation-lightweight-backbone-for","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","date":"2024-03-18","arxiv_id":"2403.11735","n_code_links":2,"syntology":null},{"paper":null,"slug":"cofinet-unveiling-camouflaged-objects-with","title":"CoFiNet: Unveiling Camouflaged Objects with Multi-Scale Finesse","date":"2024-02-03","arxiv_id":"2402.02217","n_code_links":0,"syntology":null},{"paper":"/paper/innovative-horizons-in-aerial-imagery-lsknet","slug":"innovative-horizons-in-aerial-imagery-lsknet","title":"Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for Advanced Object Detection","date":"2023-11-21","arxiv_id":"2311.12956","n_code_links":1,"syntology":null},{"paper":null,"slug":"variational-relational-point-completion-1","title":"Variational Relational Point Completion Network for Robust 3D Classification","date":"2023-04-18","arxiv_id":"2304.09131","n_code_links":0,"syntology":null},{"paper":"/paper/large-selective-kernel-network-for-remote","slug":"large-selective-kernel-network-for-remote","title":"Large Selective Kernel Network for Remote Sensing Object Detection","date":"2023-03-16","arxiv_id":"2303.09030","n_code_links":1,"syntology":null},{"paper":"/paper/esknet-an-enhanced-adaptive-selection-kernel","slug":"esknet-an-enhanced-adaptive-selection-kernel","title":"ESKNet-An enhanced adaptive selection kernel convolution for breast tumors segmentation","date":"2022-11-05","arxiv_id":"2211.02915","n_code_links":1,"syntology":null},{"paper":null,"slug":"tc-sknet-with-gridmask-for-low-complexity","title":"TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene","date":"2022-10-05","arxiv_id":"2210.02287","n_code_links":0,"syntology":null},{"paper":"/paper/ctooth-a-fully-annotated-3d-dataset-and","slug":"ctooth-a-fully-annotated-3d-dataset-and","title":"CTooth: A Fully Annotated 3D Dataset and Benchmark for Tooth Volume Segmentation on Cone Beam Computed Tomography Images","date":"2022-06-17","arxiv_id":"2206.08778","n_code_links":1,"syntology":null},{"paper":"/paper/selective-kernel-attention-for-robust-speaker","slug":"selective-kernel-attention-for-robust-speaker","title":"Frequency and Multi-Scale Selective Kernel Attention for Speaker Verification","date":"2022-04-03","arxiv_id":"2204.01005","n_code_links":1,"syntology":null},{"paper":"/paper/selective-residual-m-net-for-real-image","slug":"selective-residual-m-net-for-real-image","title":"Selective Residual M-Net for Real Image Denoising","date":"2022-03-03","arxiv_id":"2203.01645","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-based-knowledge-distillation-for","slug":"transformer-based-knowledge-distillation-for","title":"TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation","date":"2022-02-27","arxiv_id":"2202.13393","n_code_links":2,"syntology":null},{"paper":"/paper/faster-hyperspectral-image-classification","slug":"faster-hyperspectral-image-classification","title":"Faster hyperspectral image classification based on selective kernel mechanism using deep convolutional networks","date":"2022-02-14","arxiv_id":"2202.06458","n_code_links":1,"syntology":null},{"paper":"/paper/attribute-based-progressive-fusion-network","slug":"attribute-based-progressive-fusion-network","title":"Attribute-Based Progressive Fusion Network for RGBT Tracking","date":"2022-01-26","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"drpn-making-cnn-dynamically-handle-scale","title":"DRPN: Making CNN Dynamically Handle Scale Variation","date":"2021-12-21","arxiv_id":"2112.10963","n_code_links":0,"syntology":null},{"paper":"/paper/variational-relational-point-completion","slug":"variational-relational-point-completion","title":"Variational Relational Point Completion Network","date":"2021-04-20","arxiv_id":"2104.10154","n_code_links":1,"syntology":null},{"paper":"/paper/wavegrad-estimating-gradients-for-waveform","slug":"wavegrad-estimating-gradients-for-waveform","title":"WaveGrad: Estimating Gradients for Waveform Generation","date":"2020-09-02","arxiv_id":"2009.00713","n_code_links":7,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/compounding-the-performance-improvements-of","slug":"compounding-the-performance-improvements-of","title":"Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network","date":"2020-01-17","arxiv_id":"2001.06268","n_code_links":1,"syntology":{"ran":3,"of":11,"n_ran_checked":2,"n_instrument":1,"unverified":8,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","official":{"repos":["clovaai/assembled-cnn"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/selective-kernel-networks","slug":"selective-kernel-networks","title":"Selective Kernel Networks","date":"2019-03-15","arxiv_id":"1903.06586","n_code_links":20,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["implus/SKNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"papers_shown":27,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":27,"with_a_code_link":18,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":27,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/method/selective-kernel/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/selective-kernel/papers/ran/1","json":"/method/selective-kernel/papers/ran/1.json","rows":3}],"tasks":[{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":5},{"task":"/task/object-detection","name":"Object Detection","papers":4},{"task":"/task/segmentation","name":"Segmentation","papers":4},{"task":"/task/object-detection-1","name":"object-detection","papers":4},{"task":"/task/image-classification","name":"Image Classification","papers":3},{"task":"/task/object","name":"Object","papers":3},{"task":"/task/denoising","name":"Denoising","papers":2},{"task":"/task/lesion-segmentation","name":"Lesion Segmentation","papers":2},{"task":"/task/object-detection-in-aerial-images","name":"Object Detection In Aerial Images","papers":2},{"task":"/task/point-cloud-completion","name":"Point Cloud Completion","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/image-classification","name":"image-classification","papers":2},{"task":"/task/3d-classification","name":"3D Classification","papers":1},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/automl","name":"AutoML","papers":1},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":1},{"task":"/task/change-detection","name":"Change Detection","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/click-through-rate-prediction","name":"Click-Through Rate Prediction","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1}],"tasks_shown":20,"n_tasks":51,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":2},{"year":"2021","papers":2},{"year":"2022","papers":8},{"year":"2023","papers":3},{"year":"2024","papers":9},{"year":"2025","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/selective-kernel"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Selective%20Kernel","read_at":"2026-10-05T01:01:45+00:00","query":"Selective Kernel","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1903.06586","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Selective Kernel' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["Large Selective Kernel Network (LSKNet)","Kernel-WIS","RIS-Kernel","VQE-kernel","Yat kernel","Jinc kernel","Wald kernel","Kernel-UCBVI"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"e192acd12bde771c0dd80dfff34c3b29f59aa0f0f43931cc0f9b30fbeb2669f9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}