AI Paper Atlas

Research map / Continual learning / Class-incremental

First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning

Aristeidis Panos, Yuriko Kobe, Daniel Olmeda Reino, Rahaf Aljundi, Richard E. Turner

ICCV 2023 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 43 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 FiLM adaptation in the first session (ablation)FSA with EfficientNet-B0 · VTAB+ average, 50 shots (offline)accuracy: 49.9 -> 64.5Improved
add FiLM adaptation to ResNet18 backbone (ablation)ResNet18 · VTAB+ average, 50 shots (offline)accuracy: 49.6 -> 59.5Improved
meta-learning based body adaptation instead of FiLM (ablation)FSA · VTAB+ average, 50 shots (offline)accuracy: 64.5 -> 51.7Hurt
full-body adaptation instead of FiLM (ablation)FSA · VTAB+ average, 50 shots (offline)accuracy: 64.5 -> 64.9No clear effect
FiLM adaptation versus no adaptation on 50-shot CL (ablation)FSA-FiLM · CIFAR100 (50-shot CL)accuracy: 57.4 -> 70.9Improved
FSA-FiLM versus no adaptation on SVHN 50-shot CL (ablation)FSA-FiLM · SVHN (50-shot CL)accuracy: 28.3 -> 51.3Improved
FSA-FiLM versus a ConvNext pretrained on ImageNet-22K without adaptationFSA-FiLM · 50-shot CL, CIFAR100 and DomainNetaccuracy: CIFAR100 87.1 vs 70.9; SVHN 43.6 vs 51.3; dSprites-loc 13.6 vs 35.7Mixed
use 50-shot/2-way sessions instead of 10-shot/10-way (ablation)FSA-FiLM · VTAB+ average CLaccuracy: 52.6 -> 55.8Improved
FSA full-body adaptation versus FiLM in high-shot first session with many classes (ablation)FSA with EfficientNet-B0 · CIFAR100 (large first session)accuracy: 61.8 -> 66.0Improved
use FSA with full body adaptation on a small first session of 10 classes (ablation)FSA · CIFAR100 (full shots, 10-class first session)accuracy: FSA 62.8 vs FSA-FiLM 73.8 vs NA 68.2Hurt
FSA-FiLM versus FACT on CIFAR100 full-shot sessionsFSA-FiLM · CIFAR100 (full-shot, 10 classes per session)accuracy: 10.2 -> 73.8Improved
replay-free FSA-FiLM versus GDumb replay on CORE50FSA-FiLM · CORE50accuracy: 90.0 vs 85.4Hurt

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