On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “AdaIN”

AdaIN-Switchable CycleGAN for Efficient Unsupervised Low-Dose CT Denoisingeess.IV

A new cycleGAN architecture reduces memory and parameter requirements for low-dose CT denoising.

problem Efficient unsupervised low-dose CT denoising with minimal memory and parameter usage.

method Single switchable generator using AdaIN layers for efficient training and inference.

result The proposed method outperforms previous cycleGAN approaches with half the parameters.

cycleGAN low-dose CT denoising AdaIN unsupervised learning

2020-08-13abs ↗pdf ↗

Switchable Deep Beamformereess.IV

A switchable deep beamformer enables versatile image processing.

problem Training and storing separate beamformers for each application.

method Switchable deep beamformer using Adaptive Instance Normalization (AdaIN) layers.

result Single network can produce various image processing outputs.

deep beamformer adaptive instance normalization image processing ultrasound

2020-08-31abs ↗pdf ↗

Cycle-free CycleGAN using Invertible Generator for Unsupervised Low-Dose CT Denoisingeess.IV

New CycleGAN uses invertible generator for faster, less resource-intensive CT denoising.

problem Efficient unsupervised CT denoising without paired data.

method Single generator with wavelet residual domain, no discriminators, cycle consistency via invertible generator.

result Significantly improved denoising performance with faster training and less parameters.

CycleGAN CT Denoising Invertible Generator Wavelets Low-Dose Imaging

2021-04-17abs ↗pdf ↗

Federated CycleGAN for Privacy-Preserving Image-to-Image Translationcs.CV

Federated CycleGAN enables privacy-preserving image translation without central data.

problem Privacy and security issues in unsupervised image-to-image translation.

method Novel federated CycleGAN architecture that decomposes CycleGAN loss into client-specific local objectives.

result Federated CycleGAN achieves comparable performance to non-federated CycleGAN without central data exchange.

federated learning image-to-image translation privacy-preserving CycleGAN unsupervised learning

2021-06-17abs ↗pdf ↗