{"url":"/method/selective-kernel-convolution","slug":"selective-kernel-convolution","name":"Selective Kernel Convolution","full_name":"Selective Kernel Convolution","full_name_withheld":false,"description_markdown":"A **Selective Kernel Convolution** is a [convolution](https://paperswithcode.com/method/convolution) that enables neurons to adaptively adjust their RF sizes among multiple kernels with different kernel sizes. Specifically, the SK convolution has three operators – Split, Fuse and Select. Multiple branches with different kernel sizes are fused using\r\n[softmax](https://paperswithcode.com/method/softmax) attention that is guided by the information in these branches. Different attentions on these branches yield different sizes of the effective receptive fields of neurons in the fusion layer","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":"Computer Vision","area_id":"computer-vision","collection":"Convolutions","url":"/methods/category/convolutions","pwc_aliases":[]}],"n_papers_tagged":29,"archive_num_papers":29,"papers_newest_first":[{"paper":"/paper/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,"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","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,"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","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,"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,"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,"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","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","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,"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","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,"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","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","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,"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","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","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","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","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","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","title":"Attribute-Based Progressive Fusion Network for RGBT Tracking","date":"2022-01-26","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/model-based-image-signal-processors-via","title":"Model-Based Image Signal Processors via Learnable Dictionaries","date":"2022-01-10","arxiv_id":"2201.03210","n_code_links":1,"syntology":null},{"paper":null,"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","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","title":"WaveGrad: Estimating Gradients for Waveform Generation","date":"2020-09-02","arxiv_id":"2009.00713","n_code_links":7,"syntology":{"ran":1,"of":3,"unverified":2,"pointer_only":1}},{"paper":"/paper/deceiving-computers-in-reverse-turing-test","title":"Deceiving computers in Reverse Turing Test through Deep Learning","date":"2020-06-01","arxiv_id":"2006.11373","n_code_links":2,"syntology":null},{"paper":"/paper/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":1,"of":11,"unverified":10,"pointer_only":0}},{"paper":"/paper/selective-kernel-networks","title":"Selective Kernel Networks","date":"2019-03-15","arxiv_id":"1903.06586","n_code_links":20,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":3}}],"papers_shown":29,"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/denoising","name":"Denoising","papers":3},{"task":"/task/image-classification","name":"Image Classification","papers":3},{"task":"/task/object","name":"Object","papers":3},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":2},{"task":"/task/image-denoising","name":"Image 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":null,"name":"CAPTCHA Detection","papers":1},{"task":"/task/change-detection","name":"Change Detection","papers":1}],"tasks_shown":20,"n_tasks":57,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":3},{"year":"2021","papers":2},{"year":"2022","papers":9},{"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-convolution"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}