AI Paper Atlas

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

Pixel Distillation: Cost-Flexible Distillation Across Image Sizes and Heterogeneous Networks

Guangyu Guo, Dingwen Zhang, Longfei Han, Nian Liu, Ming‐Ming Cheng, Junwei Han

TPAMI 2024 · Label-efficient and robust learning › Knowledge distillation · approach: Knowledge distillation for detectors · 30 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 KD to baseline student (ablation)Baseline-FT · CUB (setting b, K=4)top-1 accuracy: 41.56 -> 49.38Improved
add ISRD to KD one-stage baseline (ablation)vanilla PD · CUB (setting b, K=4)top-1 accuracy: 49.38 -> 50.34Improved
add TAS assistant stage (ablation)vanilla PD · CUB (setting b, K=4)top-1 accuracy: 50.34 -> 51.40Improved
add ICF feature distillation in input compression stage (ablation)TAS · CUB (setting b, K=4)top-1 accuracy: 51.40 -> 52.44Improved
add ISRD to TAS-AFP (CrossKD) detector (ablation)TAS-AFP (CrossKD) · PASCAL VOC (setting h, K=4)mAP: 61.3 -> 62.9Improved
add Cao et al. FPN feature distillation (ablation)TAS-AFP (CrossKD) · COCO (setting i, K=4)mAP: 25.1 -> 24.6Hurt
add Cao et al. FPN feature distillationTAS-AFP (CrossKD) · COCO (setting i, K=2)mAP: 33.7 -> 35.0Improved
add AFP and TAS to student detectorRetinaNet student · PASCAL VOC (setting h, K=4)mAP: 56.9 -> 61.3Improved
use two-stage TAS instead of vanilla PD with DKDvanilla PD (DKD) · ImageNet (setting b, K=4)top-1 accuracy: 52.84 -> 53.83Improved
use feature distillation AT at K=4KD student · CUB (setting b, K=4)top-1 accuracy: 49.38 -> 4.55Hurt
do model compression before input compression in TAS (ablation)TAS · CUB (settings b and f)top-1 accuracyImproved
increase ISRD decoder kernel size from 1x1 to 7x7 (ablation)ISRD · CUB (setting b)top-1 accuracyHurt

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