Methods › Computer Vision › Image Model Blocks › Bottleneck Residual Block

Bottleneck Residual Block

2,049 papers tagged archive 2025-07-28

Introduced by Kaiming He et al. in Deep Residual Learning for Image Recognition

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

A Bottleneck Residual Block is a variant of the 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 architecture, and are used as part of deeper ResNets such as ResNet-50 and ResNet-101.

PaperSourceSee Code · pytorch/vision

Papers archive 2025-07-28

30 shown of 2,049, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 765 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Image Classification338
image-classification249
Semantic Segmentation190
Object Detection181
General Classification175
object-detection149
Classification135
Transfer Learning126
Self-Supervised Learning124
Representation Learning116
Contrastive Learning114
Segmentation109
Data Augmentation97
Object76
Deep Learning67
Instance Segmentation66
Quantization56
GPU52
Action Recognition46
Neural Architecture Search46

Usage over time archive 2025-07-28

Papers per year tagged with Bottleneck Residual Block: 2015 to 2025, peak 393 393 0 2015: 2 papers 2015 2016: 34 papers 2016 2017: 102 papers 2017 2018: 191 papers 2018 2019: 309 papers 2019 2020: 385 papers 2020 2021: 393 papers 2021 2022: 309 papers 2022 2023: 301 papers 2023 2024: 22 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (2,049 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Image Model BlocksSkip Connection Blocks

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections