Methods › General › Attention Modules › SCA
Semantic Cross Attention
SCA
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Semantic Cross Attention (SCA) is based on cross attention, which we restrict with respect to a semantic mask.
The goal of SCA is two-fold depending on what is the query and what is the key. Either it allows to give the feature map information from a semantically restricted set of latents or, respectively, it allows a set of latents to retrieve information in a semantically restricted region of the feature map.
SCA is defined as:
SCA(I₁, I₂, I₃) = σ((QKᵀ⊙I₃ +τ(1-I₃))/(√(dᵢₙ)))V ,
where I₁,I₂,I₃ the inputs, with I₁ attending I₂, and I₃ the mask that forces tokens from I₁ to attend only specific tokens from I₂. The attention values requiring masking are filled with -∞ before the softmax. (In practice τ=-10⁹), Q = W_QI₁, K = W_KI₂ and V = W_VI₂ the queries, keys and values, and dᵢₙ the internal attention dimension. σ(.) is the softmax operation.
Let X∈ℝ^(n×C) be the feature map with n the number of pixels, and C the number of channels. Let Z∈ℝ^(m×d) be a set of m latents of dimension d and s the number of semantic labels. Each semantic label is attributed k latents, such that m=k×s. Each semantic label mask is assigned k copies in S∈{0;1}^(n ×m).
We can differentiate 3 types of SCA:
(a) SCA with pixels X attending latents Z: SCA(X, Z, S), where W_Q ∈ ℝ^(n×dᵢₙ) and W_K, W_V ∈ ℝ^(m×dᵢₙ). The idea is to force the pixels from a semantic region to attend latents that are associated with the same label.
(b) SCA with latents Z attending pixels X: SCA(Z, X, S), where W_Q∈ ℝ^(m×dᵢₙ), W_K, W_V ∈ ℝ^(n×dᵢₙ). The idea is to semantically mask attention values to enforce latents to attend semantically corresponding pixels.
(c) SCA with latents Z attending themselves: SCA(Z, Z, M), where W_Q, W_K, W_V ∈ ℝ^(n×dᵢₙ). We denote M∈ℕ^(m×m) this mask, with Mₗₐₜₑₙₜₛ(i,j) = 1 if the semantic label of latent i is the same as the one of latent j; 0 otherwise. The idea is to let the latents only attend latents that share the same semantic label.
In Syntology repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: listed only). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2605.26971) is about this method is not checked.
Origin paper of this answer, arXiv:2605.26971 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 6 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; 6 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 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.
Papers archive 2025-07-28
archive papers tagged: 47 · with a code link: 12 · 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 47 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 47 of 47, 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.
-
UAV-Based Remote Sensing of Soil Moisture Across Diverse Land Covers: Validation and Bayesian Uncertainty Characterization 5 Jun 2025 · 0 repositories · arXiv:2506.05572
-
Pinching-Antenna Systems (PASS)-enabled Secure Wireless Communications 18 Apr 2025 · 0 repositories · arXiv:2504.13670
-
Probabilistic Stability Guarantees for Feature Attributions 18 Apr 2025 · 0 repositories · arXiv:2504.13787
-
Label Anything: An Interpretable, High-Fidelity and Prompt-Free Annotator 5 Feb 2025 · 0 repositories · arXiv:2502.02972
-
It's Not Just a Phase: On Investigating Phase Transitions in Deep Learning-based Side-channel Analysis 1 Feb 2025 · 0 repositories · arXiv:2502.00384
-
Movable Antenna-Assisted Integrated Sensing and Communication Systems 2 Jan 2025 · 0 repositories · arXiv:2501.01217
-
Make Shuffling Great Again: A Side-Channel Resistant Fisher-Yates Algorithm for Protecting Neural Networks 1 Jan 2025 · 0 repositories · arXiv:2501.00798
-
High-Throughput Detection of Risk Factors to Sudden Cardiac Arrest in Youth Athletes: A Smartwatch-Based Screening Platform 2 Dec 2024 · 0 repositories · arXiv:2412.12118
-
Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation 2 Dec 2024 · 0 repositories · arXiv:2412.01316
-
FonTS: Text Rendering with Typography and Style Controls 28 Nov 2024 · 1 repository · arXiv:2412.00136
-
Multi-task Gaze Estimation Via Unidirectional Convolution 27 Nov 2024 · 0 repositories · arXiv:2411.18061
-
Power Source Allocation for RIS-aided Integrating Sensing, Communication, and Power Transfer Systems Based on NOMA 1 Nov 2024 · 0 repositories · arXiv:2411.00334
-
Semantic Component Analysis: Discovering Patterns in Short Texts Beyond Topics 28 Oct 2024 · 1 repository · arXiv:2410.21054
-
Mutual Coupling-Aware Channel Estimation and Beamforming for RIS-Assisted Communications 5 Oct 2024 · 0 repositories · arXiv:2410.04110
-
SCA: Improve Semantic Consistent in Unrestricted Adversarial Attacks via DDPM Inversion 3 Oct 2024 · 1 repository · arXiv:2410.02240
-
Optimizing Multi-User Uplink Cooperative Rate-Splitting Multiple Access: Efficient User Pairing and Resource Allocation 3 Sep 2024 · 0 repositories · arXiv:2409.02276
-
FAS vs. ARIS: Which Is More Important for FAS-ARIS Communication Systems? 17 Aug 2024 · 0 repositories · arXiv:2408.09067
-
Fluid-Antenna Enhanced ISAC: Joint Antenna Positioning and Dual-Functional Beamforming Design under Perfect and Imperfect CSI 25 Jul 2024 · 0 repositories · arXiv:2407.18988
-
Side-Channel Analysis of OpenVINO-based Neural Network Models 23 Jul 2024 · 0 repositories · arXiv:2407.16467
-
Multi-Functional Beamforming Design for Integrated Sensing, Communication, and Computation 1 Jul 2024 · 0 repositories · arXiv:2407.01006
-
Brain Tumor Classification using Vision Transformer with Selective Cross-Attention Mechanism and Feature Calibration 25 Jun 2024 · 0 repositories · arXiv:2406.17670
-
Depth linear discrimination-oriented feature selection method based on adaptive sine cosine algorithm for software defect prediction 20 May 2024 · 1 repository
-
Impedance vs. Power Side-channel Vulnerabilities: A Comparative Study 10 May 2024 · 0 repositories · arXiv:2405.06242
-
Special Characters Attack: Toward Scalable Training Data Extraction From Large Language Models 9 May 2024 · 0 repositories · arXiv:2405.05990
-
Causality-Aware Spatiotemporal Graph Neural Networks for Spatiotemporal Time Series Imputation 18 Mar 2024 · 0 repositories · arXiv:2403.11960
-
SNOW-SCA: ML-assisted Side-Channel Attack on SNOW-V 13 Mar 2024 · 0 repositories · arXiv:2403.08267
-
Precise Extraction of Deep Learning Models via Side-Channel Attacks on Edge/Endpoint Devices 5 Mar 2024 · 0 repositories · arXiv:2403.02870
-
A Review and Comparison of AI Enhanced Side Channel Analysis 3 Feb 2024 · 0 repositories · arXiv:2402.02299
-
On the Sum Secrecy Rate Maximisation for Wireless Vehicular Networks 31 Jan 2024 · 0 repositories · arXiv:2401.17522
-
Energy-Efficient Power Allocation in Cell-Free Massive MIMO via Graph Neural Networks 25 Jan 2024 · 1 repository · arXiv:2401.14281
-
Linguistic-Based Mild Cognitive Impairment Detection Using Informative Loss 23 Jan 2024 · 0 repositories · arXiv:2402.01690
-
Efficient Wireless Federated Learning via Low-Rank Gradient Factorization 15 Jan 2024 · 1 repository · arXiv:2401.07496
-
Joint User Association, Interference Cancellation and Power Control for Multi-IRS Assisted UAV Communications 8 Dec 2023 · 0 repositories · arXiv:2312.04786
-
Enhancing Object Coherence in Layout-to-Image Synthesis 17 Nov 2023 · 1 repository · arXiv:2311.10522
-
Investigating Efficient Deep Learning Architectures For Side-Channel Attacks on AES 22 Sep 2023 · 0 repositories · arXiv:2309.13170
-
Sparsity-Aware Distributed Learning for Gaussian Processes with Linear Multiple Kernel 15 Sep 2023 · 1 repository · arXiv:2309.08201
-
Fixed Inter-Neuron Covariability Induces Adversarial Robustness 7 Aug 2023 · 0 repositories · arXiv:2308.03956
-
Multi-Granularity Detector for Vulnerability Fixes 23 May 2023 · 2 repositories · arXiv:2305.13884
-
Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding 19 May 2023 · 0 repositories · arXiv:2305.11392
-
Bitstream-Corrupted JPEG Images are Restorable: Two-stage Compensation and Alignment Framework for Image Restoration 14 Apr 2023 · 1 repository · arXiv:2304.06976Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples)
-
Side-channel analysis against ANSSI’s protected AES implementation on ARM: end-to-end attacks with multi-task learning 10 Mar 2023 · 1 repository
-
Wireless Powered Short Packet Communications with Multiple WPT Sources 24 Feb 2023 · 0 repositories · arXiv:2302.12396
-
NASCTY: Neuroevolution to Attack Side-channel Leakages Yielding Convolutional Neural Networks 25 Jan 2023 · 0 repositories · arXiv:2301.10802
-
Energy Efficiency Optimization of Intelligent Reflective Surface-assisted Terahertz-RSMA System 21 Nov 2022 · 0 repositories · arXiv:2211.11271
-
A Framework for Mutual Information-based MIMO Integrated Sensing and Communication Beamforming Design 15 Nov 2022 · 0 repositories · arXiv:2211.07887
-
Compressive Spectrum Sensing Using Sampling-Controlled Block Orthogonal Matching Pursuit 14 Nov 2022 · 0 repositories · arXiv:2211.07095
-
SCAM! Transferring humans between images with Semantic Cross Attention Modulation 10 Oct 2022 · 1 repository · arXiv:2210.04883
Tasks archive 2025-07-28
20 shown of 47 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