Methods › General › Attention Mechanisms › DANet
Dual Attention Network
DANet
Introduced by Jun Fu et al. in Dual Attention Network for Scene Segmentation
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
In the field of scene segmentation, encoder-decoder structures cannot make use of the global relationships between objects, whereas RNN-based structures heavily rely on the output of the long-term memorization. To address the above problems, Fu et al. proposed a novel framework, the dual attention network (DANet), for natural scene image segmentation. Unlike CBAM and BAM, it adopts a self-attention mechanism instead of simply stacking convolutions to compute the spatial attention map, which enables the network to capture global information directly.
DANet uses in parallel a position attention module and a channel attention module to capture feature dependencies in spatial and channel domains. Given the input feature map X, convolution layers are applied first in the position attention module to obtain new feature maps. Then the position attention module selectively aggregates the features at each position using a weighted sum of features at all positions, where the weights are determined by feature similarity between corresponding pairs of positions. The channel attention module has a similar form except for dimensional reduction to model cross-channel relations. Finally the outputs from the two branches are fused to obtain final feature representations. For simplicity, we reshape the feature map X to C×(H ×W) whereupon the overall process can be written as Q, K, V = W_qX, WₖX, WᵥX Yᵖᵒˢ = X+ VSoftmax(QᵀK) Yᶜʰⁿ = X+ Softmax(XXᵀ)X Y = Yᵖᵒˢ + Yᶜʰⁿ where W_q, Wₖ, Wᵥ ∈ℝ^(C×C) are used to generate new feature maps.
The position attention module enables DANet to capture long-range contextual information and adaptively integrate similar features at any scale from a global viewpoint, while the channel attention module is responsible for enhancing useful channels as well as suppressing noise. Taking spatial and channel relationships into consideration explicitly improves the feature representation for scene segmentation. However, it is computationally costly, especially for large input feature maps.
Papers archive 2025-07-28
10 shown of 10, 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.
-
ECG Arrhythmia Detection Using Disease-specific Attention-based Deep Learning Model 25 Jul 2024 · 0 repositories · arXiv:2407.18033
-
Rethinking Residual Connection in Training Large-Scale Spiking Neural Networks 9 Nov 2023 · 0 repositories · arXiv:2311.05171
-
Distractor-aware Event-based Tracking 22 Oct 2023 · 0 repositories · arXiv:2310.14194
-
Improving Deep Attractor Network by BGRU and GMM for Speech Separation 7 Aug 2023 · 0 repositories · arXiv:2308.03332
-
Monocular Depth Distribution Alignment with Low Computation 9 Mar 2022 · 1 repository · arXiv:2203.04538
-
DANets: Deep Abstract Networks for Tabular Data Classification and Regression 6 Dec 2021 · 1 repository · arXiv:2112.02962
-
Invertible Denoising Network: A Light Solution for Real Noise Removal 21 Apr 2021 · 1 repository · arXiv:2104.10546Syntology ran 3 of 3 samples · 0 unverified
-
Multi-Attention-Network for Semantic Segmentation of Fine Resolution Remote Sensing Images 3 Sep 2020 · 0 repositories · arXiv:2009.02130
-
Attention Scaling for Crowd Counting 1 Jun 2020 · 0 repositories
-
Dual Attention Network for Scene Segmentation 9 Sep 2018 · 12 repositories · arXiv:1809.02983Syntology ran 0 of 7 samples · 7 unverified · 5 pointer-only (licence)
Tasks archive 2025-07-28
20 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
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