AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Partial Weight Adaptation for Robust DNN Inference

Xiufeng Xie, Kyu-Han Kim

CVPR 2020 · Architectures and efficiency › RNNs and normalization · approach: Efficient network compression and training · 3 citations (OpenAlex)

Check 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
Adapt distortion-sensitive weights for each JPEG quality instead of using one fixed modelDRN-D-22 · Cityscapes, 10 JPEG qualitiesaverage accuracy: 18.12%Improved
Adapt distortion-sensitive weights for each JPEG quality instead of mixed trainingDRN-D-22 · Cityscapes, 10 JPEG qualitiesaverage accuracy: 1.95%Improved
Adapt distortion-sensitive weights for each resolution instead of using one fixed modelDRN-D-38 · Cityscapes, 7 H.264 resolutionsaverage accuracy: 2.88%Improved
Adapt distortion-sensitive weights for each resolution instead of mixed trainingDRN-D-38 · Cityscapes, 7 H.264 resolutionsaverage accuracy: 1.70%Improved
Adapt distortion-sensitive weights for each brightness level instead of using one fixed modelDRN-D-38 · Cityscapes, 20 brightness levelsaverage accuracy: 5.11%Improved
Adapt distortion-sensitive weights for each brightness level instead of mixed trainingDRN-D-38 · Cityscapes, 20 brightness levelsaverage accuracy: 1.11%Improved
Adapt distortion-sensitive weights for each JPEG quality instead of using one fixed modelMask R-CNN with ResNet-50 · Penn-Fudan, 10 JPEG qualities, pedestrian segmentationaverage accuracy: 5.16%Improved
Adapt distortion-sensitive weights for each JPEG quality instead of using one fixed modelMask R-CNN with ResNet-50 · Penn-Fudan, 10 JPEG qualities, bounding box detectionaverage accuracy: 3.53%Improved
Adapt distortion-sensitive weights for each JPEG quality instead of mixed trainingMask R-CNN with ResNet-50 · Penn-Fudan, 10 JPEG qualities, pedestrian segmentationaverage accuracy: 1.20%Improved
Adapt distortion-sensitive weights for each JPEG quality instead of mixed trainingMask R-CNN with ResNet-50 · Penn-Fudan, 10 JPEG qualities, bounding box detectionaverage accuracy: 1.33%Improved
Adapt distortion-sensitive weights for each H.264 distortion level rather than use stability trainingDRN-D-38 · Cityscapes, H.264 compressionaverage accuracy: 4.84%Improved
Adapt only 0.2% of DRN weights rather than fully fine-tune the model (ablation)DRN-D-38 · Distorted-data frequency responsefrequency response similarity: 0.2%No clear effect

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