AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

DDSF: Robust Few-Shot Learning via Disentangled Subspaces with Determinantal Point Process

Xulun Ye, Yifan Mei, Kun Zhou, Zelei Wu, Jieyu Zhao

CVPR 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification

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 diversity-only anomaly filter pk (ablation)DDSF baseline · OOD-polluted Meta-Dataset (30% noise)accuracy: 77.1 -> 79.4Improved
add cohesion-only anomaly filter qk (ablation)DDSF baseline · OOD-polluted Meta-Dataset (30% noise)accuracy: 77.1 -> 79.5Improved
fuse pk and qk into score sk (ablation)DDSF baseline · OOD-polluted Meta-Dataset (30% noise)accuracy: 77.1 -> 80.7Improved
add DPP-guided diffusion repair of flagged outliers (ablation)DDSF with filter sk · OOD-polluted Meta-Dataset (30% noise)accuracy: 80.7 -> 83.4Improved
replace orthogonal loss with DPP unique volume loss Lun (ablation)DDSF with filter and repair · OOD-polluted Meta-Dataset (30% noise)accuracy: 83.4 -> 85.3Improved
replace orthogonal loss with DPP unique volume loss Lun (ablation)DDSF with filter and repair · OOD-polluted Meta-Dataset (0% noise)accuracy: 89.9 -> 91.9Improved
add foreground masking via U-2-Net (ablation)DDSF · Meta-Dataset 0% / 30% OOD / 30% SLSaccuracy: 91.9 -> 92.1; 85.3 -> 85.2; 83.2 -> 83.5No clear effect
raise anomaly threshold tau from 0.3 to 0.6 (ablation)DDSF · 30% OOD noiseaccuracy: 85.1 -> 80.8Hurt
lower tau to 0.1 vs 0.3 (ablation)DDSF · 30% OOD noiseaccuracy: 84.5 vs 85.1No clear effect
vary loss weights lambda_sh and lambda_un (ablation)DDSF · Meta-Dataset 0% noiseaccuracy: lowest 88.11No clear effect
use DDSF instead of DETA++ at 70% OOD noiseSwinT backbone · OOD-polluted Meta-Dataset (70% noise)accuracy: 47.0 -> 61.6Improved
use DDSF instead of DETA++ under symmetric label swapping noiseSwinT backbone · 30% SLS noiseaccuracy: 75.1 -> 83.2Improved

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