AI Paper Atlas

Research map / Continual learning / Class-incremental

PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning

Arthur Douillard, Matthieu Cord, Charles Ollion, Thomas Robert, Eduardo Valle

ECCV 2020 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 754 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 POD-spatial on intermediate features (on top of POD-flat) (ablation)PODNet LSC · CIFAR100 50 steps (NME)average incremental accuracy: 53.29 -> 61.40Improved
add POD-flat on the final embedding (ablation)LSC classifier · CIFAR100 50 steps (NME)average incremental accuracy: 41.56 -> 53.29Improved
replace cosine classifier with LSC (ablation)PODNet with POD-flat and POD-spatial · CIFAR100 50 steps (NME)average incremental accuracy: 56.69 -> 61.40Improved
replace cosine classifier with LSC (ablation)PODNet with POD-flat and POD-spatial · CIFAR100 50 steps (CNN)average incremental accuracy: 55.72 -> 57.98Improved
use NCA-based loss instead of cross-entropy for LSC (ablation)PODNet · CIFAR100 50 steps (NME)average incremental accuracy: 59.86 -> 61.40Improved
use POD-pixels instead of no intermediate distillation (ablation)LSC with POD-flat · CIFAR100 50 steps (NME)average incremental accuracy: 53.29 -> 49.74Hurt
use POD-spatial instead of POD-width alone (ablation)LSC with POD-flat · CIFAR100 50 steps (NME)average incremental accuracy: 60.92 -> 61.40Improved
use Perceptual Style distillation instead of none (ablation)LSC with POD-flat · CIFAR100 50 steps (NME)average incremental accuracy: 53.29 -> 51.01Hurt
use GradCam distillation instead of none (ablation)LSC with POD-flat · CIFAR100 50 steps (CNN)average incremental accuracy: 52.98 -> 52.48No clear effect
add POD-flat when POD-spatial is already used (ablation)LSC with POD-spatial · CIFAR100 50 steps (NME)average incremental accuracy: 61.42 -> 61.40No clear effect
use 10 proxies per class instead of 1 (ablation)LSC · CIFAR100 50 steps (CNN)average incremental accuracy: 56.80 -> 57.98Improved
add POD-spatial on top of POD-flat (ablation)PODNet · CIFAR100 old vs new classesaccuracy: +7 p.p. old classes; -0.2 p.p. new classesMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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