Methods › Computer Vision › Image Model Blocks › Residual Block

Residual Block

2,807 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.

Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced as part of the ResNet architecture.

Formally, denoting the desired underlying mapping as ℋ(x), we let the stacked nonlinear layers fit another mapping of ℱ(x):=ℋ(x)-x. The original mapping is recast into ℱ(x)+x. The ℱ(x) acts like a residual, hence the name 'residual block'.

The intuition is that it is easier to optimize the residual mapping than to optimize the original, unreferenced mapping. To the extreme, if an identity mapping were optimal, it would be easier to push the residual to zero than to fit an identity mapping by a stack of nonlinear layers. Having skip connections allows the network to more easily learn identity-like mappings.

Note that in practice, Bottleneck Residual Blocks are used for deeper ResNets, such as ResNet-50 and ResNet-101, as these bottleneck blocks are less computationally intensive.

PaperSourceSee Code · pytorch/vision

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: Residual-MII; Residual-ICM; Residual SODAP; Ladder-Residual; Residual Paving; horizon residual; Residual Algebra; Residual Alignment.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 2,807 · with a code link: 1,322 · where Syntology ran a sample: 375 (314 with a run with no instrument failure, 61 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (375 of 2,807 tagged: 314 with a run with no instrument failure, 61 where every run was a failure of Syntology's instrument)

Page 1 of 29: papers 1 to 100 of 2,807, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 922 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 Classification361
image-classification265
Semantic Segmentation228
Object Detection202
General Classification182
object-detection169
Classification147
Segmentation146
Transfer Learning139
Data Augmentation135
Translation127
Self-Supervised Learning126
Representation Learning124
Contrastive Learning123
Image Generation121
Image-to-Image Translation100
Object87
Generative Adversarial Network84
Super-Resolution83
Deep Learning80

Usage over time archive 2025-07-28

Papers per year tagged with Residual Block: 2015 to 2025, peak 523 523 0 2015: 2 papers 2015 2016: 35 papers 2016 2017: 117 papers 2017 2018: 236 papers 2018 2019: 384 papers 2019 2020: 523 papers 2020 2021: 500 papers 2021 2022: 437 papers 2022 2023: 426 papers 2023 2024: 104 papers 2024 2025: 43 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (2,807 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