AI Paper Atlas

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

Denoising-Enhanced Coarse-to-Fine Infrared Small Target Detection with Attention Prior-Guided Knowledge Distillation

Houzhang Fang, Ruixuan Huang, Qiuhuan Chen, Xiaolin Wang, Yi Chang, Luxin Yan

ECCV 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Knowledge distillation for detectors · 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 denoising-assisted training (DAT) (ablation)ECFNet baseline · UAVAP50: 87.26 -> 92.71Improved
add attention prior-guided KD (APKD) (ablation)ECFNet baseline · UAVAP50: 87.26 -> 89.30Improved
combine DAT and APKD (ablation)ECFNet · UAVAP50: 92.71 -> 95.87Improved
inject target-like noise into GT mask (full DAT) vs concatenating GT mask (ablation)RBCN · UAVCRP: 92.62 -> 94.13Improved
use 20x20 grid instead of 40x40 (ablation)RBCN · UAVAP50: 81.62 -> 95.7Improved
use 20x20 instead of 10x10 grid (ablation)RBCN · UAVAP50: 93.84 -> 95.7Improved
insert DAT in all three RBCN blocks (ablation)RBCN · UAVCRP: 89.38 -> 94.13Improved
insert DAT only in block 2 (ablation)RBCN · UAVCRR: 93.45 -> 91.36Hurt
use C2fP instead of Swin Transformer in RBCN (ablation)RBCN · UAVCRP / FLOPs: CRP 96.22 -> 94.13; FLOPs 34.5 -> 8.9Mixed
use APKD instead of other KD methods (Plain, DRKD, CrossKD, DCSF) (ablation)fine-stage student · UAVAP50: best other 91.15 -> 95.87Improved
apply other KD methods (DRKD, CrossKD, DCSF) without attention prior (ablation)fine-stage student · UAVAP50: 92.71 -> 87.70 (CrossKD)Hurt
change teacher among five models (ablation)APKD · UAVAP50: 92.71 -> 92.54 to 95.87Improved

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