Methods › General › Attention Mechanisms › DANet

Dual Attention Network

DANet

10 papers tagged archive 2025-07-28

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.

PaperSource

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.

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.

TaskPapers
Segmentation2
Semantic Segmentation2
Arrhythmia Detection1
Crowd Counting1
Deep Learning1
Denoising1
Depth Estimation1
Diagnostic1
Image Denoising1
Management1
Monocular Depth Estimation1
Object1
Object Tracking1
Position1
Scene Segmentation1
Speech Separation1
Thermal Image Segmentation1
Visual Object Tracking1
global-optimization1
regression1

Usage over time archive 2025-07-28

Papers per year tagged with DANet: 2018 to 2024, peak 3 3 0 2018: 1 paper 2018 2019: 0 papers 2019 2020: 2 papers 2020 2021: 2 papers 2021 2022: 1 paper 2022 2023: 3 papers 2023 2024: 1 paper 2024
Papers per year the archive tags with this method, by the paper's archive date (10 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

Attention Mechanisms

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