AI Paper Atlas

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

Knowledge Distillation for Learned Image Compression

Yunuo Chen, Zezheng Lyu, Bing He, Ning Cao, Gang Chen, Guo Lu, Wenjun Zhang

ICCV 2025 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 8 citations (OpenAlex)

Read the paper

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 knowledge distillation to pruned student (ablation)KDIC · KodakBD-rate (%): -11.21 -> -13.71Improved
add knowledge distillation to pruned student (ablation)KDIC · CLICBD-rate (%): -10.05 -> -12.63Improved
add knowledge distillation to pruned student (ablation)KDIC · TecnickBD-rate (%): -13.92 -> -16.64Improved
prune teacher into student (40% fewer parameters, 57% fewer FLOPs) (ablation)KDIC · KodakBD-rate (%): -14.28 -> -13.71No clear effect
use stage-wise implicit supervision instead of end-to-end RD + MSE feature loss (ablation)KDIC · KodakBD-rate (%): -11.22 -> -13.91Improved
use finer six-stage split instead of two-stage encoder/decoder implicit supervision (ablation)KDIC · KodakBD-rate (%): -12.74 -> -13.91Improved
use implicit end-to-end RD supervision instead of explicit MSE feature supervision (ablation)KDIC · KodakBD-rate (%): -12.07 -> -13.91Improved
align teacher and student architecture (hybrid teacher for hybrid student) (ablation)KDIC · KodakBD-rate (%): -11.01 -> -13.71Improved
add distillation to Conv-KD student (ablation)Conv-KD (S2C-Conv) · KodakBD-rate (%): -8.77 -> -11.49Improved
add distillation to TCM-KD student (ablation)TCM-KD (TCM-L) · KodakBD-rate (%): -7.49 -> -9.79Improved
KDIC versus MLIC++ and TCM-L complexityKDIC · 2K imagesparameters: 116.48 -> 47.61Improved

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