{"url":"/method/inverted-residual-block","slug":"inverted-residual-block","name":"Inverted Residual Block","full_name":"Inverted Residual Block","full_name_withheld":false,"description_markdown":"An **Inverted Residual Block**, sometimes called an **MBConv Block**, is a type of residual block used for image models that uses an inverted structure for efficiency reasons. It was originally proposed for the [MobileNetV2](https://paperswithcode.com/method/mobilenetv2) CNN architecture. It has since been reused for several mobile-optimized CNNs.\r\n\r\nA traditional [Residual Block](https://paperswithcode.com/method/residual-block) has a wide -> narrow -> wide structure with the number of channels. The input has a high number of channels, which are compressed with a [1x1 convolution](https://paperswithcode.com/method/1x1-convolution). The number of channels is then increased again with a 1x1 [convolution](https://paperswithcode.com/method/convolution) so input and output can be added. \r\n\r\nIn contrast, an Inverted Residual Block follows a narrow -> wide -> narrow approach, hence the inversion. We first widen with a 1x1 convolution, then use a 3x3 [depthwise convolution](https://paperswithcode.com/method/depthwise-convolution) (which greatly reduces the number of parameters), then we use a 1x1 convolution to reduce the number of channels so input and output can be added.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1801.04381v4","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/pytorch/vision/blob/1aef87d01eec2c0989458387fa04baebcc86ea7b/torchvision/models/mobilenet.py#L45","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":[]}],"n_papers_tagged":823,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/efficientfer-efficientnetv2-based-deep","title":"EfficientFER: EfficientNetv2 Based Deep Learning Approach for Facial Expression Recognition","date":"2025-06-02","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Deep Learning-Based Breast Cancer Detection in Mammography: A Multi-Center Validation Study in Thai Population","date":"2025-05-29","arxiv_id":"2506.03177","n_code_links":0,"syntology":null},{"paper":null,"title":"Deep Learning-Based BMD Estimation from Radiographs with Conformal Uncertainty Quantification","date":"2025-05-28","arxiv_id":"2505.22551","n_code_links":0,"syntology":null},{"paper":null,"title":"Intelligent Incident Hypertension Prediction in Obstructive Sleep Apnea","date":"2025-05-27","arxiv_id":"2505.20615","n_code_links":0,"syntology":null},{"paper":null,"title":"Deep Learning for Breast Cancer Detection: Comparative Analysis of ConvNeXT and EfficientNet","date":"2025-05-24","arxiv_id":"2505.18725","n_code_links":0,"syntology":null},{"paper":null,"title":"SuperPure: Efficient Purification of Localized and Distributed Adversarial Patches via Super-Resolution GAN Models","date":"2025-05-22","arxiv_id":"2505.16318","n_code_links":0,"syntology":null},{"paper":null,"title":"An Approach Towards Identifying Bangladeshi Leaf Diseases through Transfer Learning and XAI","date":"2025-05-21","arxiv_id":"2505.16033","n_code_links":0,"syntology":null},{"paper":null,"title":"An Exploratory Approach Towards Investigating and Explaining Vision Transformer and Transfer Learning for Brain Disease Detection","date":"2025-05-21","arxiv_id":"2505.16039","n_code_links":0,"syntology":null},{"paper":null,"title":"Comprehensive Lung Disease Detection Using Deep Learning Models and Hybrid Chest X-ray Data with Explainable AI","date":"2025-05-21","arxiv_id":"2505.16028","n_code_links":0,"syntology":null},{"paper":"/paper/vulnerability-of-transfer-learned-neural","title":"Vulnerability of Transfer-Learned Neural Networks to Data Reconstruction Attacks in Small-Data Regime","date":"2025-05-20","arxiv_id":"2505.14323","n_code_links":1,"syntology":null},{"paper":null,"title":"Defect Detection in Photolithographic Patterns Using Deep Learning Models Trained on Synthetic Data","date":"2025-05-15","arxiv_id":"2505.10192","n_code_links":0,"syntology":null},{"paper":null,"title":"Real-World fNIRS-Based Brain-Computer Interfaces: Benchmarking Deep Learning and Classical Models in Interactive Gaming","date":"2025-05-15","arxiv_id":"2505.10536","n_code_links":0,"syntology":null},{"paper":"/paper/v-efficientnets-vector-valued-efficiently","title":"V-EfficientNets: Vector-Valued Efficiently Scaled Convolutional Neural Network Models","date":"2025-05-08","arxiv_id":"2505.05659","n_code_links":1,"syntology":null},{"paper":"/paper/anomalymatch-discovering-rare-objects-of","title":"AnomalyMatch: Discovering Rare Objects of Interest with Semi-supervised and Active Learning","date":"2025-05-06","arxiv_id":"2505.03509","n_code_links":1,"syntology":null},{"paper":null,"title":"Comparative Analysis of Lightweight Deep Learning Models for Memory-Constrained Devices","date":"2025-05-06","arxiv_id":"2505.03303","n_code_links":0,"syntology":null},{"paper":null,"title":"PROM: Prioritize Reduction of Multiplications Over Lower Bit-Widths for Efficient CNNs","date":"2025-05-06","arxiv_id":"2505.03254","n_code_links":0,"syntology":null},{"paper":null,"title":"Diagnostic Uncertainty in Pneumonia Detection using CNN MobileNetV2 and CNN from Scratch","date":"2025-05-05","arxiv_id":"2505.02396","n_code_links":0,"syntology":null},{"paper":null,"title":"CSASN: A Multitask Attention-Based Framework for Heterogeneous Thyroid Carcinoma Classification in Ultrasound Images","date":"2025-05-04","arxiv_id":"2505.02211","n_code_links":0,"syntology":null},{"paper":null,"title":"Local Herb Identification Using Transfer Learning: A CNN-Powered Mobile Application for Nepalese Flora","date":"2025-05-04","arxiv_id":"2505.02147","n_code_links":0,"syntology":null},{"paper":null,"title":"Conformal Prediction for Indoor Positioning with Correctness Coverage Guarantees","date":"2025-05-03","arxiv_id":"2505.01810","n_code_links":0,"syntology":null},{"paper":"/paper/soft-label-caching-and-sharpening-for","title":"Soft-Label Caching and Sharpening for Communication-Efficient Federated Distillation","date":"2025-04-28","arxiv_id":"2504.19602","n_code_links":1,"syntology":null},{"paper":null,"title":"VeLU: Variance-enhanced Learning Unit for Deep Neural Networks","date":"2025-04-21","arxiv_id":"2504.15051","n_code_links":0,"syntology":null},{"paper":null,"title":"Time Frequency Analysis of EMG Signal for Gesture Recognition using Fine grained Features","date":"2025-04-20","arxiv_id":"2504.14708","n_code_links":0,"syntology":null},{"paper":"/paper/deep-ensembling-of-multiband-images-for-earth","title":"Deep Ensembling of Multiband Images for Earth Remote Sensing and Foramnifera Data","date":"2025-04-02","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/training-frozen-feature-pyramid-dinov2-for","title":"Training Frozen Feature Pyramid DINOv2 for Eyelid Measurements with Infinite Encoding and Orthogonal Regularization","date":"2025-04-01","arxiv_id":"2504.00515","n_code_links":1,"syntology":null},{"paper":null,"title":"Camera Model Identification with SPAIR-Swin and Entropy based Non-Homogeneous Patches","date":"2025-03-28","arxiv_id":"2503.22120","n_code_links":0,"syntology":null},{"paper":null,"title":"Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach","date":"2025-03-28","arxiv_id":"2503.22251","n_code_links":0,"syntology":null},{"paper":null,"title":"An improved EfficientNetV2 for garbage classification","date":"2025-03-27","arxiv_id":"2503.21208","n_code_links":0,"syntology":null},{"paper":"/paper/face-spoofing-detection-using-deep-learning","title":"Face Spoofing Detection using Deep Learning","date":"2025-03-25","arxiv_id":"2503.19223","n_code_links":1,"syntology":null},{"paper":null,"title":"Deep learning-based identification of precipitation clouds from all-sky camera data for observatory safety","date":"2025-03-24","arxiv_id":"2503.18670","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":161},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":126},{"task":"/task/image-classification","name":"image-classification","papers":117},{"task":"/task/object-detection","name":"Object Detection","papers":86},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":74},{"task":"/task/object-detection-1","name":"object-detection","papers":74},{"task":"/task/classification-1","name":"Classification","papers":61},{"task":"/task/quantization","name":"Quantization","papers":59},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":56},{"task":"/task/deep-learning","name":"Deep Learning","papers":47},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":42},{"task":"/task/diagnostic","name":"Diagnostic","papers":38},{"task":"/task/classification","name":"General Classification","papers":37},{"task":null,"name":"GPU","papers":35},{"task":"/task/segmentation","name":"Segmentation","papers":28},{"task":"/task/decoder","name":"Decoder","papers":20},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":19},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":19},{"task":"/task/model-compression","name":"Model Compression","papers":19},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":18}],"tasks_shown":20,"n_tasks":414,"usage_by_year":[{"year":"2018","papers":14},{"year":"2019","papers":73},{"year":"2020","papers":118},{"year":"2021","papers":160},{"year":"2022","papers":129},{"year":"2023","papers":139},{"year":"2024","papers":136},{"year":"2025","papers":54}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/inverted-residual-block"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}