Methods › General › Skip Connections › Residual Connection

Residual Connection

28,401 papers tagged archive 2025-07-28

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

Residual Connections are a type of skip-connection that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions.

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 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.

Source: Deep Residual Learning for Image RecognitionSee Code · pytorch/vision

Papers archive 2025-07-28

30 shown of 28,401, 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 2,748 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
Language Modelling3,004
Language Modeling2,347
Retrieval1,822
Question Answering1,485
Decoder1,483
Sentence1,340
RAG1,293
Semantic Segmentation1,199
Translation1,159
Retrieval-augmented Generation1,126
Image Classification1,121
Object Detection1,073
object-detection955
Transfer Learning933
Machine Translation932
image-classification872
Large Language Model834
Segmentation822
Classification784
Representation Learning767

Usage over time archive 2025-07-28

Papers per year tagged with Residual Connection: 2015 to 2025, peak 7,243 7,243 0 2015: 1 paper 2015 2016: 46 papers 2016 2017: 160 papers 2017 2018: 414 papers 2018 2019: 1556 papers 2019 2020: 2835 papers 2020 2021: 3816 papers 2021 2022: 3936 papers 2022 2023: 5815 papers 2023 2024: 7243 papers 2024 2025: 2579 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (28,401 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

Skip Connections

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