AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

CLIDD: Cross-Layer Independent Deformable Description for Efficient and Discriminative Local Feature Representation

Haodi Yao, Fenghua He, Ning Hao, Yao Su

IJCV 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Patient consistent distillation · 0 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 cross-layer predictor instead of single-layer offset prediction (ablation)CLIDD U128 · MegaDepth-1500AUC@10: 75.51 -> 77.15Improved
add cross-layer predictor instead of single-layer offset prediction (ablation)CLIDD A48 · MegaDepth-1500AUC@10: 56.20 -> 57.13Improved
add layer-independent sampler instead of shared sampler (ablation)CLIDD U128 · MegaDepth-1500AUC@10: 75.80 -> 77.15Improved
add layer-independent sampler instead of shared sampler (ablation)CLIDD A48 · MegaDepth-1500AUC@10: 55.22 -> 57.13Improved
use CLIDD instead of Full-Scale SDDH head (ablation)U128 · MegaDepth-1500AUC@10: 75.63 -> 77.15Improved
use CLIDD instead of Sub-Scale Vanilla head (ablation)A48 · MegaDepth-1500AUC@10: 36.39 -> 57.13Improved
use CLIDD instead of Full-Scale Vanilla head (ablation)U128 · MegaDepth-1500AUC@10: 67.89 -> 77.15Improved
add Procrustes distillation (w_OP=1) to DualSoftmax (ablation)A48 · MegaDepth-1500AUC@10: 46.65 -> 57.13Improved
add DualSoftmax loss (w_DS=0.05) to pure distillation (ablation)A48 · MegaDepth-1500AUC@10: 55.93 -> 57.13Improved
add distillation to direct loss for larger model (ablation)T64 · MegaDepth-1500AUC@10: 66.44 -> 66.74No clear effect
replace ALIKED-N32 teacher with U128 teacher (ablation)A48 · MegaDepth-1500AUC@10: 57.13 -> 58.53No clear effect
replace SDDH with CLIDD on frozen ALIKED-N32 (ablation)ALIKED-N32 · MegaDepth-1500AUC@10: 73.56 -> 74.40Improved

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