Methods › Computer Vision › Image Models › Res2Net
Res2Net
Introduced by Shang-Hua Gao et al. in Res2Net: A New Multi-scale Backbone Architecture
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Res2Net is an image model that employs a variation on bottleneck residual blocks. The motivation is to be able to represent features at multiple scales. This is achieved through a novel building block for CNNs that constructs hierarchical residual-like connections within one single residual block. This represents multi-scale features at a granular level and increases the range of receptive fields for each network layer.
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='1904.01169'). Repositories: 34 listed of 34 in the graph, strongest link: mentioned on GitHub. The lookup matched a paper by its title, arXiv:1904.01169, not a method entry. This answer is about arXiv:1904.01169, the paper the archive credits with this method.
Origin paper of this answer, arXiv:1904.01169 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified (of 9 harvested samples) · 9 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
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.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 25 · with a code link: 15 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (1 of 25 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 25 of 25, 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.
-
Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofing 8 Apr 2025 · 1 repository · arXiv:2504.05657
-
ERes2NetV2: Boosting Short-Duration Speaker Verification Performance with Computational Efficiency 4 Jun 2024 · 0 repositories · arXiv:2406.02167
-
Speech enhancement deep-learning architecture for efficient edge processing 27 May 2024 · 0 repositories · arXiv:2405.16834
-
Enhancing Retinal Vascular Structure Segmentation in Images With a Novel Design Two-Path Interactive Fusion Module Model 3 Mar 2024 · 1 repository · arXiv:2403.01362
-
NeXt-TDNN: Modernizing Multi-Scale Temporal Convolution Backbone for Speaker Verification 14 Dec 2023 · 1 repository · arXiv:2312.08603
-
Improving Short Utterance Anti-Spoofing with AASIST2 15 Sep 2023 · 0 repositories · arXiv:2309.08279
-
A region and category confidence-based multi-task network for carotid ultrasound image segmentation and classification 2 Jul 2023 · 0 repositories · arXiv:2307.00583
-
Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection 27 Jun 2023 · 0 repositories · arXiv:2306.15389
-
An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verification 22 May 2023 · 2 repositories · arXiv:2305.12838
-
Breaking Through the Haze: An Advanced Non-Homogeneous Dehazing Method based on Fast Fourier Convolution and ConvNeXt 8 May 2023 · 1 repository · arXiv:2305.04430
-
Cross-modal information fusion for voice spoofing detection 1 Feb 2023 · 1 repository
-
Synthetic Voice Detection and Audio Splicing Detection using SE-Res2Net-Conformer Architecture 7 Oct 2022 · 0 repositories · arXiv:2210.03581
-
Breast Cancer Classification Based on Histopathological Images Using a Deep Learning Capsule Network 1 Aug 2022 · 0 repositories · arXiv:2208.00594
-
Frequency and Multi-Scale Selective Kernel Attention for Speaker Verification 3 Apr 2022 · 1 repository · arXiv:2204.01005
-
MFSNet: A Multi Focus Segmentation Network for Skin Lesion Segmentation 27 Mar 2022 · 2 repositories · arXiv:2203.14341
-
Phase-Aware Spoof Speech Detection Based on Res2Net with Phase Network 21 Mar 2022 · 0 repositories · arXiv:2203.10793
-
Pushing the limits of raw waveform speaker recognition 16 Mar 2022 · 2 repositories · arXiv:2203.08488
-
Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attacks 19 Jul 2021 · 2 repositories · arXiv:2107.08803
-
DW-GAN: A Discrete Wavelet Transform GAN for NonHomogeneous Dehazing 18 Apr 2021 · 1 repository · arXiv:2104.08911
-
Partially-Connected Differentiable Architecture Search for Deepfake and Spoofing Detection 7 Apr 2021 · 1 repository · arXiv:2104.03123
-
The xx205 System for the VoxCeleb Speaker Recognition Challenge 2020 31 Oct 2020 · 0 repositories · arXiv:2011.00200
-
Replay and Synthetic Speech Detection with Res2net Architecture 28 Oct 2020 · 2 repositories · arXiv:2010.15006
-
Gated Res2Net for Multivariate Time Series Analysis 19 Sep 2020 · 1 repository · arXiv:2009.11705
-
Improved Res2Net model for Person re-identification 8 Oct 2019 · 0 repositories · arXiv:1910.04061
-
Res2Net: A New Multi-scale Backbone Architecture 2 Apr 2019 · 34 repositories · arXiv:1904.01169Syntology 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified (of 9 harvested samples) · 9 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 45 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Speaker Verification | 9 |
| Segmentation | 3 |
| Face Swapping | 2 |
| Semantic Segmentation | 2 |
| Speaker Recognition | 2 |
| Automatic Speech Recognition | 1 |
| Binary Classification | 1 |
| Cancer Classification | 1 |
| Classification | 1 |
| Computational Efficiency | 1 |
| Data Augmentation | 1 |
| Decoder | 1 |
| Deep Learning | 1 |
| DeepFake Detection | 1 |
| Dimensionality Reduction | 1 |
| Feature Engineering | 1 |
| GPU | 1 |
| Generative Adversarial Network | 1 |
| Graph Attention | 1 |
| Image Classification | 1 |
Usage over time archive 2025-07-28
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
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