AI Paper Atlas

Research map / Continual learning / Class-incremental

Towards Realistic Evaluation of Industrial Continual Learning Scenarios with an Emphasis on Energy Consumption and Computational Footprint

Vivek Chavan, Paul Koch, Marian Schlüter, Clemens Briese

ICCV 2023 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 12 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
introduce periodic joint training update (JTupdate) to incremental learning (ablation)DER · InVar-100 six-month studyAUCacc: 0.72 -> 0.80Improved
introduce JTupdate (ablation)DER · InVar-100 six-month studyPFLOPs: 1.61E15 -> 1.22E15Improved
introduce JTupdate (ablation)POD-AANet · InVar-100 six-month studyAUCacc: 0.64 -> 0.78Improved
introduce JTupdate (ablation)PODNet · InVar-100 six-month studyAUCacc: 0.58 -> 0.67Improved
use incremental learning rather than cumulative joint trainingCIL methods · ImageNet-Subsetenergy (kWh): 33.29 -> 6.12 (FOSTER)Improved
use incremental learning rather than cumulative joint trainingCIL methods · ImageNet-Subsetaverage accuracy (%): 83.7 -> 72.4 (DER best)Hurt
increase rehearsal memory to 2000 per subcategory (ablation)CIL methods · InVar-100 Experiment 3accuracy and energy: average accuracy up to 90.45; energy up to 23.2 kWhMixed
increase clutter in image context (cluttered vs white background)CIL methods · InVar-100 Experiment 2average incremental accuracy: DER 90.3% -> 58.6%Hurt
compare accuracy-only reporting versus adding energy and FLOPsCIL evaluation · ImageNet-Subsetenergy (kWh): DER 72.4% at 15.08 kWh vs FOSTER 69.8% at 6.12 kWhMixed

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