AI Paper Atlas

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

HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous Learning

Xuerui Zhang, Xuehao Wang, Zhan Zhuang, Linglan Zhao, Ziyue Li, Xinmin Zhang, Zhihuan Song, Yu Zhang

CVPR 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 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 distribution-balanced loss (DB-HAD) (ablation)HAD · NYUv2avg relative improvement: -2.84% when removedImproved
add salience-guided loss (SG-HAD) (ablation)HAD · NYUv2avg relative improvement: -1.27% when removedImproved
use geometric instead of arithmetic mean within groups (ablation)HAD · NYUv2avg relative improvement: -6.29% with arithmeticImproved
use binary foreground/background grouping instead of equal-interval groups for regression (ablation)HAD · NYUv2avg relative improvement: -3.64% (5), -5.43% (10), -9.72% (15) groupsImproved
distill into full network (DIS) instead of updating only decoders or only new decoder (ablation)HAD · NYUv2avg relative improvement: -7.76%, -6.65%, -10.94% for alternativesImproved
HAD vs EWC on NYUv2 ResNet-18lifelong learner · NYUv2avg relative improvement: +24.39% -> +32.74%Improved
use larger encoder ResNet-50 with HADHAD · NYUv2avg relative improvement: +32.74% -> +35.71%Improved
sequential HAD vs separate task-specific modelsHAD · NYUv2per-task improvement: +1.38% seg, +5.2% depth, +9.87% normalImproved

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