{"url":"/method/bottleneck-residual-block","slug":"bottleneck-residual-block","name":"Bottleneck Residual Block","full_name":"Bottleneck Residual Block","full_name_withheld":false,"description_markdown":"A **Bottleneck Residual Block** is a variant of the [residual block](https://paperswithcode.com/method/residual-block) that utilises 1x1 convolutions to create a bottleneck. The use of a bottleneck reduces the number of parameters and matrix multiplications. The idea is to make residual blocks as thin as possible to increase depth and have less parameters. They were introduced as part of the [ResNet](https://paperswithcode.com/method/resnet) architecture, and are used as part of deeper ResNets such as ResNet-50 and ResNet-101.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Deep Residual Learning for Image Recognition","paper":"/paper/deep-residual-learning-for-image-recognition","first_author":"Kaiming He","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/deep-residual-learning-for-image-recognition"},"source":{"url":"http://arxiv.org/abs/1512.03385v1","title":"Deep Residual Learning for Image Recognition","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":2049,"archive_num_papers":2049,"papers_newest_first":[{"paper":null,"title":"Deep Distance Map Regression Network with Shape-aware Loss for Imbalanced Medical Image Segmentation","date":"2025-01-15","arxiv_id":"2501.09116","n_code_links":0,"syntology":null},{"paper":"/paper/scale-invariance-of-graph-neural-networks","title":"Scale Invariance of Graph Neural Networks","date":"2024-11-28","arxiv_id":"2411.19392","n_code_links":1,"syntology":null},{"paper":"/paper/scalenet-scale-invariance-learning-in","title":"ScaleNet: Scale Invariance Learning in Directed Graphs","date":"2024-11-13","arxiv_id":"2411.08758","n_code_links":1,"syntology":null},{"paper":null,"title":"LR-Net: A Lightweight and Robust Network for Infrared Small Target Detection","date":"2024-08-05","arxiv_id":"2408.02780","n_code_links":0,"syntology":null},{"paper":"/paper/sernet-former-semantic-segmentation-by","title":"SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks","date":"2024-01-28","arxiv_id":"2401.15741","n_code_links":2,"syntology":null},{"paper":"/paper/paratranscnn-parallelized-transcnn-encoder","title":"ParaTransCNN: Parallelized TransCNN Encoder for Medical Image Segmentation","date":"2024-01-27","arxiv_id":"2401.15307","n_code_links":1,"syntology":null},{"paper":null,"title":"Attention-based Efficient Classification for 3D MRI Image of Alzheimer's Disease","date":"2024-01-25","arxiv_id":"2401.14130","n_code_links":0,"syntology":null},{"paper":"/paper/a-systematic-approach-to-robustness-modelling","title":"A Training Rate and Survival Heuristic for Inference and Robustness Evaluation (TRASHFIRE)","date":"2024-01-24","arxiv_id":"2401.13751","n_code_links":1,"syntology":null},{"paper":null,"title":"Detecting and recognizing characters in Greek papyri with YOLOv8, DeiT and SimCLR","date":"2024-01-23","arxiv_id":"2401.12513","n_code_links":0,"syntology":null},{"paper":"/paper/image-based-human-re-identification-which","title":"Image-based human re-identification: Which covariates are actually (the most) important?","date":"2024-01-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Cross-modality Guidance-aided Multi-modal Learning with Dual Attention for MRI Brain Tumor Grading","date":"2024-01-17","arxiv_id":"2401.09029","n_code_links":0,"syntology":null},{"paper":null,"title":"Hybrid of DiffStride and Spectral Pooling in Convolutional Neural Networks","date":"2024-01-17","arxiv_id":"2401.09008","n_code_links":0,"syntology":null},{"paper":null,"title":"Residual Alignment: Uncovering the Mechanisms of Residual Networks","date":"2024-01-17","arxiv_id":"2401.09018","n_code_links":0,"syntology":null},{"paper":null,"title":"BanglaNet: Bangla Handwritten Character Recognition using Ensembling of Convolutional Neural Network","date":"2024-01-16","arxiv_id":"2401.08035","n_code_links":0,"syntology":null},{"paper":null,"title":"Harnessing Machine Learning for Discerning AI-Generated Synthetic Images","date":"2024-01-14","arxiv_id":"2401.07358","n_code_links":0,"syntology":null},{"paper":null,"title":"NODI: Out-Of-Distribution Detection with Noise from Diffusion","date":"2024-01-13","arxiv_id":"2401.08689","n_code_links":0,"syntology":null},{"paper":null,"title":"Triamese-ViT: A 3D-Aware Method for Robust Brain Age Estimation from MRIs","date":"2024-01-13","arxiv_id":"2401.09475","n_code_links":0,"syntology":null},{"paper":"/paper/always-sparse-training-by-growing-connections","title":"Always-Sparse Training by Growing Connections with Guided Stochastic Exploration","date":"2024-01-12","arxiv_id":"2401.06898","n_code_links":1,"syntology":null},{"paper":null,"title":"Enhancing Contrastive Learning with Efficient Combinatorial Positive Pairing","date":"2024-01-11","arxiv_id":"2401.05730","n_code_links":0,"syntology":null},{"paper":null,"title":"Adaptive-avg-pooling based Attention Vision Transformer for Face Anti-spoofing","date":"2024-01-10","arxiv_id":"2401.04953","n_code_links":0,"syntology":null},{"paper":"/paper/automated-detection-of-myopic-maculopathy-in","title":"Automated Detection of Myopic Maculopathy in MMAC 2023: Achievements in Classification, Segmentation, and Spherical Equivalent Prediction","date":"2024-01-08","arxiv_id":"2401.03615","n_code_links":1,"syntology":null},{"paper":null,"title":"A Cost-Efficient FPGA Implementation of Tiny Transformer Model using Neural ODE","date":"2024-01-05","arxiv_id":"2401.02721","n_code_links":0,"syntology":null},{"paper":"/paper/gps-ssl-guided-positive-sampling-to-inject","title":"GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning","date":"2024-01-03","arxiv_id":"2401.01990","n_code_links":1,"syntology":null},{"paper":null,"title":"Block Pruning for Enhanced Efficiency in Convolutional Neural Networks","date":"2023-12-28","arxiv_id":"2312.16904","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-physics-based-learned","title":"Efficient Physics-Based Learned Reconstruction Methods for Real-Time 3D Near-Field MIMO Radar Imaging","date":"2023-12-28","arxiv_id":"2312.16959","n_code_links":1,"syntology":null},{"paper":"/paper/cr-sam-curvature-regularized-sharpness-aware","title":"CR-SAM: Curvature Regularized Sharpness-Aware Minimization","date":"2023-12-21","arxiv_id":"2312.13555","n_code_links":1,"syntology":{"ran":7,"of":11,"unverified":4,"pointer_only":11}},{"paper":null,"title":"SPDGAN: A Generative Adversarial Network based on SPD Manifold Learning for Automatic Image Colorization","date":"2023-12-21","arxiv_id":"2312.13506","n_code_links":0,"syntology":null},{"paper":"/paper/unlocking-deep-learning-a-bp-free-approach","title":"Unlocking Deep Learning: A BP-Free Approach for Parallel Block-Wise Training of Neural Networks","date":"2023-12-20","arxiv_id":"2312.13311","n_code_links":1,"syntology":null},{"paper":null,"title":"Voxceleb-ESP: preliminary experiments detecting Spanish celebrities from their voices","date":"2023-12-20","arxiv_id":"2401.09441","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-play-starcraft-ii","title":"Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach","date":"2023-12-19","arxiv_id":"2312.11865","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":2}}],"papers_shown":30,"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":338},{"task":"/task/image-classification","name":"image-classification","papers":249},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":190},{"task":"/task/object-detection","name":"Object Detection","papers":181},{"task":"/task/classification","name":"General Classification","papers":175},{"task":"/task/object-detection-1","name":"object-detection","papers":149},{"task":"/task/classification-1","name":"Classification","papers":135},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":126},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":124},{"task":"/task/representation-learning","name":"Representation Learning","papers":116},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":114},{"task":"/task/segmentation","name":"Segmentation","papers":109},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":97},{"task":"/task/object","name":"Object","papers":76},{"task":"/task/deep-learning","name":"Deep Learning","papers":67},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":66},{"task":"/task/quantization","name":"Quantization","papers":56},{"task":null,"name":"GPU","papers":52},{"task":"/task/action-recognition-in-videos","name":"Action Recognition","papers":46},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":46}],"tasks_shown":20,"n_tasks":765,"usage_by_year":[{"year":"2015","papers":2},{"year":"2016","papers":34},{"year":"2017","papers":102},{"year":"2018","papers":191},{"year":"2019","papers":309},{"year":"2020","papers":385},{"year":"2021","papers":393},{"year":"2022","papers":309},{"year":"2023","papers":301},{"year":"2024","papers":22},{"year":"2025","papers":1}],"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/bottleneck-residual-block"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}