Methods › Computer Vision › Image Model Blocks › Res2Net Block
Res2Net Block
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.
A Res2Net Block is an image model block that constructs hierarchical residual-like connections within one single residual block. It was proposed as part of the Res2Net CNN architecture.
The block represents multi-scale features at a granular level and increases the range of receptive fields for each network layer. The 3 ×3 filters of n channels is replaced with a set of smaller filter groups, each with w channels. These smaller filter groups are connected in a hierarchical residual-like style to increase the number of scales that the output features can represent. Specifically, we divide input feature maps into several groups. A group of filters first extracts features from a group of input feature maps. Output features of the previous group are then sent to the next group of filters along with another group of input feature maps.
This process repeats several times until all input feature maps are processed. Finally, feature maps from all groups are concatenated and sent to another group of 1 ×1 filters to fuse information altogether. Along with any possible path in which input features are transformed to output features, the equivalent receptive field increases whenever it passes a 3 ×3 filter, resulting in many equivalent feature scales due to combination effects.
One way of thinking of these blocks is that they expose a new dimension, scale, alongside the existing dimensions of depth, width, and cardinality.
Papers archive 2025-07-28
25 shown of 25, 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.
-
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 ran 3 of 9 samples · 6 unverified · 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