Methods › Computer Vision › Semantic Segmentation Modules › Channel-wise Cross Attention
Channel-wise Cross Attention
Introduced by Haonan Wang et al. in UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Channel-wise Cross Attention is a module for semantic segmentation used in the UCTransNet architecture. It is used to fuse features of inconsistent semantics between the Channel Transformer and U-Net decoder. It guides the channel and information filtration of the Transformer features and eliminates the ambiguity with the decoder features.
Mathematically, we take the i-th level Transformer output Oᵢ ∈ℝ^(C×H×W) and i-th level decoder feature map Dᵢ ∈ℝ^(C×H×W) as the inputs of Channel-wise Cross Attention. Spatial squeeze is performed by a global average pooling (GAP) layer, producing vector 𝒢(X) ∈ℝ^(C×1×1) with its $k$th channel 𝒢(X) = 1/(H×W)∑ᴴᵢ₌₁∑ᵂⱼ₌₁Xᵏ(i, j). We use this operation to embed the global spatial information and then generate the attention mask:
Mᵢ = L₁ ·𝒢(Oᵢ) + L₂ ·𝒢(Dᵢ)
where L₁ ∈ℝ^(C×C) and L₂ ∈ℝ^(C×C) and being weights of two Linear layers and the ReLU operator δ(·). This operation in the equation above encodes the channel-wise dependencies. Following ECA-Net which empirically showed avoiding dimensionality reduction is important for learning channel attention, the authors use a single Linear layer and sigmoid function to build the channel attention map. The resultant vector is used to recalibrate or excite Oᵢ to O̅ᵢ = σ(Mᵢ) ·Oᵢ, where the activation σ(Mᵢ) indicates the importance of each channel. Finally, the masked O̅ᵢ is concatenated with the up-sampled features of the i-th level decoder.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: framewise addition and cross-attention mechanisms; Spatial and Channel-wise Attention Autoencoder (SCAAE); Cross-Validated Cross-Channel Self-Attention and Denoising; Dense pixel-wise Cross-query-and-support Attention weighted Mask Aggregation (DCAMA); endto-end instance-wise and prototype-wise contrastive learning model with cross-attention mechanism; channel-wise entropy model with parameter-efficient swin-transformer-based attention (SWAtten) modules; Dual Cross Attention; cross-channel module.
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.
Papers archive 2025-07-28
archive papers tagged: 5 · with a code link: 5 · where Syntology ran a sample: 2 (0 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 5 tagged: 0 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 5 of 5, 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.
-
Enhancing Conditional Image Generation with Explainable Latent Space Manipulation 29 Aug 2024 · 1 repository · arXiv:2408.16232
-
Boosting Medical Image Segmentation Performance with Adaptive Convolution Layer 17 Apr 2024 · 1 repository · arXiv:2404.11361
-
ACC-UNet: A Completely Convolutional UNet model for the 2020s 25 Aug 2023 · 1 repository · arXiv:2308.13680
-
LViT: Language meets Vision Transformer in Medical Image Segmentation 29 Jun 2022 · 1 repository · arXiv:2206.14718Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer 9 Sep 2021 · 3 repositories · arXiv:2109.04335Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
Tasks archive 2025-07-28
11 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