AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edge

Yu Zhang, Xi Zhang, Hualin zhou, Xinyuan Chen, Shang Gao, Hong Jia, Jianfei Yang, Yuankai Qi, Tao Gu

ICML 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Efficient ViT adaptation

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 LWS layer-wise search on top of SRR (Our-Single vs SRR) (ablation)XTransfer · HHAR (5-shot)accuracy (%): 61.8 -> 71.8Improved
add layer channel removal to SRR (ablation)XTransfer SRR · HHAR (5-shot)accuracy (%): 63.6 -> 61.8Mixed
add feature space alignment (class pairing) to repair loss (ablation)XTransfer repair · HHAR initial-layer repairspeed of repair loss decrease: 1.87 times fasterImproved
use PCA anchor space with repair loss (ablation)XTransfer repair loss · HHAR (5-shot)accuracy (%): 69.33 -> 71.85Improved
use repair loss with PCA instead of MMD loss (ablation)XTransfer · HHAR (3/5/10-shot average)accuracy (%): 65.89 -> 71.85Improved
use standard PCA instead of sparse PCA (ablation)XTransfer · HHAR (5-shot)accuracy (%): 64.67 -> 71.85Improved
use PCA-#2 instead of PCA-Max (ablation)XTransfer · HHAR (3/5/10-shot)accuracy (%): average drop of 4.5% for PCA-Max vs PCA-80%Improved
use Repair loss instead of N-Pair and Triplet loss (ablation)XTransfer · HHAR (5-shot)S-score: 0.2 vs 0.05 and 0.07Improved
use proposed layer channel removal instead of L2-based pruning (ablation)XTransfer · HHAR (5-shot)average S-score: 0.1 average S-scoreImproved
add pre-search check and dynamic search range (Multi-Efficient vs Multi-Pre) (ablation)XTransfer Multi-ResNet18 search · HHARaccuracy and search time: reduces search time by 2.1 to 4 timesImproved
use only pre-search check (Multi-Pre) instead of Multi (ablation)XTransfer Multi-ResNet18 search · HHARaccuracy (%): degraded accuracy by 3.36% and 7.94%Hurt
use Image source instead of Text, Audio or Sensing source models (ablation)XTransfer · HHAR (3- to 10-shot)accuracy (%): 70.5% vs 69.6%, 64.3%, 67%Improved

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