AI Paper Atlas

Research map / Image generation / Image restoration

TS-DDAE: A novel Temporal-Spectral Denoising Diffusion AutoEncoder for Wireless Signal Recognition Model Pre-training

Yaoqi Liu, Jin Wang, Hui Wang, Chuan Shi

ICLR 2026 · Image generation › Image restoration · approach: Diffusion priors for denoising and deblurring

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the temporal encoder (ablation)TS-DDAE · RML2016.10Aoverall accuracy: 48.81 -> 63.61Improved
add the temporal encoder (ablation)TS-DDAE · RML2016.10Boverall accuracy: 50.94 -> 65.50Improved
add the spectral encoder (ablation)TS-DDAE · TechRecoverall accuracy: 37.48 -> 89.62Improved
add the spectral encoder (ablation)TS-DDAE · RML2016.10Aoverall accuracy: 62.97 -> 63.61Improved
add the interactive process between temporal and spectral encoders (ablation)TS-DDAE · TechRecoverall accuracy: 87.87 -> 89.62Improved
add the interactive process between temporal and spectral encoders (ablation)TS-DDAE · RML2016.10Boverall accuracy: 65.09 -> 65.50Improved
use two noise levels instead of a single noise (ablation)TS-DDAE · RML2016.10Aoverall accuracy: 63.01 -> 63.61Improved
use two noise levels instead of a single noise (ablation)TS-DDAE · TechRecoverall accuracy: 89.27 -> 89.62Improved
vary noise balance lambda from 0.2 to 1.0 (ablation)TS-DDAE · RML2016.10Aaccuracy: 62.22 -> 63.23Mixed
fine-tune the whole model instead of linear probeTS-DDAE · TechRecaverage accuracy: 86.00 -> 89.62Improved
fine-tune with full training data instead of 100-shotTS-DDAE · RML2016.10Aaverage accuracy: 55.47 -> 63.61Improved
use TS-DDAE pre-training instead of IQFormerTS-DDAE · RML2018average accuracy: 40.22 -> 64.15Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy