AI Paper Atlas

Research map / Detection and segmentation / CNN features

Fast Neural Network Adaptation via Parameter Remapping and Architecture Search

Jiemin Fang*, Yuzhu Sun*, Kangjian Peng*, Qian Zhang, Yuan Li, Wenyu Liu, Xinggang Wang

ICLR 2020 · Detection and segmentation › CNN features · approach: Efficient network training and design · 14 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
Adapt MobileNetV2 parameters and architecture with FNAMobileNetV2 in DeepLabv3 on Cityscapes · CityscapesmIOU (%): 75.5 -> 76.6Improved
Adapt MobileNetV2 with FNARetinaNet on MS-COCO · MS-COCOmAP (%): 33.3 -> 33.9Improved
Adapt MobileNetV2 with FNASSDLite on MS-COCO · MS-COCOmAP (%): 22.1 -> 23.3Improved
Add parameter remapping before architecture adaptation (ablation)FNA on Cityscapes with DeepLabv3 · CityscapesmIOU (%): 76.0 -> 76.6Improved
Add parameter remapping before parameter adaptation (ablation)FNA on Cityscapes with DeepLabv3 · CityscapesmIOU (%): 73.0 -> 76.6Improved
Add remapping before both architecture and parameter adaptation (ablation)FNA on Cityscapes with DeepLabv3 · CityscapesmIOU (%): 72.4 -> 76.6Improved
Use remapping rather than ImageNet pretraining before parameter adaptation (ablation)FNA on Cityscapes with DeepLabv3 · CityscapesmIOU (%): 76.5 -> 76.6Improved
Replace differentiable search with random search (ablation)FNA on RetinaNet · MS-COCOmAP (%): 33.9 -> 33.5Hurt
Add parameter remapping before architecture search (ablation)Random-search FNA on RetinaNet · MS-COCOmAP (%): 31.5 -> 33.5Improved
Add parameter remapping before parameter adaptation (ablation)Random-search FNA on RetinaNet · MS-COCOmAP (%): 25.3 -> 33.5Improved
Select width channels by batch-normalization statistics rather than FNA's basic remapping (ablation)Parameter remapping on Cityscapes with DeepLabv3 · CityscapesmIOU (%): 76.6 -> 75.8Hurt
Select width channels by weight standard deviation rather than FNA's basic remapping (ablation)Parameter remapping on Cityscapes with DeepLabv3 · CityscapesmIOU (%): 76.6 -> 75.8Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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