AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

A Simple yet Mighty Hartley Diffusion Versatilist for Generalizable Dense Vision Tasks

Qi Bi, Jingjun Yi, Huimin Huang, Hao Zheng, Haolan Zhan, Wei Ji, Yawen Huang, Yuexiang Li, Yefeng Zheng

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 2 citations (OpenAlex)

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 low-frequency training process (LTP) to DDP baseline (ablation)DDP baseline · DGSS trained on SYNTHIA (C, B, M)mIoU: 1.5%, 1.7% and 1.3%Improved
add high-frequency sampling process (HSP) to DDP baseline (ablation)DDP baseline · DGSS trained on SYNTHIA (C, B, M)mIoU: 0.9%, 1.2% and 0.5%Improved
add both LTP and HSP to DDP baseline (ablation)DDP baseline · DGSS trained on SYNTHIA (avg)mIoU: 54.7 -> 57.8Improved
inject V[0,10%) in training only (ablation)HarDiff · DGSS trained on SYNTHIA (avg)mIoU: 54.7 -> 56.2Improved
inject V[0,10%) in both training and sampling (ablation)HarDiff · DGSS trained on SYNTHIA (avg)mIoU: 54.7 -> 56.8Improved
inject V[90%,100%) in sampling only (ablation)HarDiff · DGSS trained on SYNTHIA (avg)mIoU: 54.7 -> 55.6Improved
inject V[90%,100%) in both training and sampling (ablation)HarDiff · DGSS trained on SYNTHIA (avg)mIoU: 54.7 -> 56.1Improved
inject both bands in both training and sampling instead of low in training and high in sampling (ablation)HarDiff · DGSS trained on SYNTHIA (avg)mIoU: 57.8 -> 57.6Hurt
use DHT instead of FFT, DCT or Haar wavelet (ablation)HarDiff · DGSS S to C, B, MmIoUImproved
remove highest-frequency band V[0,10%) in band-rejection analysis (ablation)ConvNeXt binary classifier · Trained on RESIDE, source/target accuracyaccuracyHurt

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