{"url":"/method/resnext-block","slug":"resnext-block","name":"ResNeXt Block","full_name":"ResNeXt Block","full_name_withheld":false,"description_markdown":"A **ResNeXt Block** is a type of [residual block](https://paperswithcode.com/method/residual-block) used as part of the [ResNeXt](https://paperswithcode.com/method/resnext) CNN architecture. It uses a \"split-transform-merge\" strategy (branched paths within a single module) similar to an [Inception module](https://paperswithcode.com/method/inception-module), i.e. it aggregates a set of transformations. Compared to a Residual Block, it exposes a new dimension,  *cardinality* (size of set of transformations) $C$, as an essential factor in addition to depth and width. \r\n\r\nFormally, a set of aggregated transformations can be represented as: $\\mathcal{F}(x)=\\sum_{i=1}^{C}\\mathcal{T}_i(x)$, where $\\mathcal{T}_i(x)$ can be an arbitrary function. Analogous to a simple neuron, $\\mathcal{T}_i$ should project $x$ into an (optionally low-dimensional) embedding and then transform it.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Aggregated Residual Transformations for Deep Neural Networks","paper":"/paper/aggregated-residual-transformations-for-deep","first_author":"Saining Xie","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/aggregated-residual-transformations-for-deep"},"source":{"url":"http://arxiv.org/abs/1611.05431v2","title":"Aggregated Residual Transformations for Deep Neural Networks","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/pytorch/vision/blob/1aef87d01eec2c0989458387fa04baebcc86ea7b/torchvision/models/resnet.py#L75","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Model Blocks","url":"/methods/category/image-model-blocks","pwc_aliases":[]},{"area":"General","area_id":"general","collection":"Skip Connection Blocks","url":"/methods/category/skip-connection-blocks","pwc_aliases":[]}],"n_papers_tagged":132,"archive_num_papers":132,"papers_newest_first":[{"paper":null,"title":"Automated MRI Tumor Segmentation using hybrid U-Net with Transformer and Efficient Attention","date":"2025-06-18","arxiv_id":"2506.15562","n_code_links":0,"syntology":null},{"paper":null,"title":"Segmenting Bi-Atrial Structures Using ResNext Based Framework","date":"2025-02-28","arxiv_id":"2503.02892","n_code_links":0,"syntology":null},{"paper":null,"title":"Collaborative Optimization in Financial Data Mining Through Deep Learning and ResNeXt","date":"2024-12-23","arxiv_id":"2412.17314","n_code_links":0,"syntology":null},{"paper":null,"title":"Pairwise Discernment of AffectNet Expressions with ArcFace","date":"2024-12-01","arxiv_id":"2412.01860","n_code_links":0,"syntology":null},{"paper":null,"title":"Recognition of Harmful Phytoplankton from Microscopic Images using Deep Learning","date":"2024-09-19","arxiv_id":"2409.12900","n_code_links":0,"syntology":null},{"paper":null,"title":"RoBERTa, ResNeXt and BiLSTM with self-attention: The ultimate trio for customer sentiment analysis","date":"2024-07-25","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/peneo-unifying-line-extraction-line-grouping","title":"PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction","date":"2024-01-07","arxiv_id":"2401.03472","n_code_links":1,"syntology":null},{"paper":"/paper/web-diagnosis-for-covid-19-and-pneumonia","title":"Web Diagnosis for COVID-19 and Pneumonia Based on Computed Tomography Scans and X-rays","date":"2024-01-06","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"title":"ProtoNER: Few shot Incremental Learning for Named Entity Recognition using Prototypical Networks","date":"2023-10-03","arxiv_id":"2310.02372","n_code_links":0,"syntology":null},{"paper":null,"title":"Predicting mechanical properties of Carbon Nanotube (CNT) images Using Multi-Layer Synthetic Finite Element Model Simulations","date":"2023-07-16","arxiv_id":"2307.07912","n_code_links":0,"syntology":null},{"paper":null,"title":"Multi-Channel Attentive Feature Fusion for Radio Frequency Fingerprinting","date":"2023-03-19","arxiv_id":"2303.10691","n_code_links":0,"syntology":null},{"paper":null,"title":"Weakly Supervised Learning with Automated Labels from Radiology Reports for Glioma Change Detection","date":"2022-10-18","arxiv_id":"2210.09698","n_code_links":0,"syntology":null},{"paper":"/paper/delving-into-the-estimation-shift-of-batch","title":"Delving into the Estimation Shift of Batch Normalization in a Network","date":"2022-03-21","arxiv_id":"2203.10778","n_code_links":1,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":0}},{"paper":"/paper/coded-resnext-a-network-for-designing","title":"Towards Disentangling Information Paths with Coded ResNeXt","date":"2022-02-10","arxiv_id":"2202.05343","n_code_links":1,"syntology":null},{"paper":null,"title":"Collision Detection: An Improved Deep Learning Approach Using SENet and ResNext","date":"2022-01-13","arxiv_id":"2201.04766","n_code_links":0,"syntology":null},{"paper":"/paper/rethink-dilated-convolution-for-real-time","title":"Rethinking Dilated Convolution for Real-time Semantic Segmentation","date":"2021-11-18","arxiv_id":"2111.09957","n_code_links":3,"syntology":null},{"paper":"/paper/a-cross-modal-fusion-network-based-on-self","title":"A cross-modal fusion network based on self-attention and residual structure for multimodal emotion recognition","date":"2021-11-03","arxiv_id":"2111.02172","n_code_links":1,"syntology":null},{"paper":null,"title":"SCA Net: Sparse Channel Attention Module for Action Recognition","date":"2021-10-15","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Stochastic Anderson Mixing for Nonconvex Stochastic Optimization","date":"2021-10-04","arxiv_id":"2110.01543","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-action-recognition-using-confidence","title":"Efficient Action Recognition Using Confidence Distillation","date":"2021-09-05","arxiv_id":"2109.02137","n_code_links":0,"syntology":null},{"paper":"/paper/group-fisher-pruning-for-practical-network","title":"Group Fisher Pruning for Practical Network Compression","date":"2021-08-02","arxiv_id":"2108.00708","n_code_links":2,"syntology":null},{"paper":"/paper/volnet-estimating-human-body-part-volumes","title":"VolNet: Estimating Human Body Part Volumes from a Single RGB Image","date":"2021-07-05","arxiv_id":"2107.02259","n_code_links":0,"syntology":null},{"paper":null,"title":"Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic","date":"2021-06-27","arxiv_id":"2106.14190","n_code_links":0,"syntology":null},{"paper":null,"title":"CUAB: Convolutional Uncertainty Attention Block Enhanced the Chest X-ray Image Analysis","date":"2021-05-05","arxiv_id":"2105.01840","n_code_links":0,"syntology":null},{"paper":"/paper/students-are-the-best-teacher-exit-ensemble","title":"Students are the Best Teacher: Exit-Ensemble Distillation with Multi-Exits","date":"2021-04-01","arxiv_id":"2104.00299","n_code_links":1,"syntology":null},{"paper":null,"title":"3M: Multi-style image caption generation using Multi-modality features under Multi-UPDOWN model","date":"2021-03-20","arxiv_id":"2103.11186","n_code_links":0,"syntology":null},{"paper":"/paper/danish-fungi-2020-not-just-another-image","title":"Danish Fungi 2020 -- Not Just Another Image Recognition Dataset","date":"2021-03-18","arxiv_id":"2103.10107","n_code_links":1,"syntology":null},{"paper":null,"title":"Depth Evaluation for Metal Surface Defects by Eddy Current Testing using Deep Residual Convolutional Neural Networks","date":"2021-03-08","arxiv_id":"2104.02472","n_code_links":0,"syntology":null},{"paper":"/paper/webface260m-a-benchmark-unveiling-the-power","title":"WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition","date":"2021-03-06","arxiv_id":"2103.04098","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-connection-of-benford-s-law-and-neural","title":"Rethinking Neural Networks With Benford's Law","date":"2021-02-05","arxiv_id":"2102.03313","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":39},{"task":"/task/image-classification","name":"Image Classification","papers":28},{"task":"/task/object-detection-1","name":"object-detection","papers":25},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":24},{"task":"/task/segmentation","name":"Segmentation","papers":20},{"task":"/task/classification","name":"General Classification","papers":19},{"task":"/task/image-classification","name":"image-classification","papers":16},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":15},{"task":"/task/object","name":"Object","papers":14},{"task":"/task/classification-1","name":"Classification","papers":8},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":8},{"task":"/task/action-recognition-in-videos","name":"Action Recognition","papers":7},{"task":"/task/panoptic-segmentation","name":"Panoptic Segmentation","papers":6},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":5},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":5},{"task":"/task/real-time-object-detection","name":"Real-Time Object Detection","papers":5},{"task":"/task/2d-object-detection","name":"2D Object Detection","papers":4},{"task":"/task/action-classification","name":"Action Classification","papers":4},{"task":"/task/deep-learning","name":"Deep Learning","papers":4},{"task":null,"name":"GPU","papers":4}],"tasks_shown":20,"n_tasks":161,"usage_by_year":[{"year":"2016","papers":2},{"year":"2017","papers":8},{"year":"2018","papers":27},{"year":"2019","papers":43},{"year":"2020","papers":19},{"year":"2021","papers":18},{"year":"2022","papers":4},{"year":"2023","papers":3},{"year":"2024","papers":6},{"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/resnext-block"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}