AI Paper Atlas

Research map / Continual learning / Class-incremental

SS-IL: Separated Softmax for Incremental Learning

Hongjoon Ahn, Jihwan Kwak, Subin Lim, Hyeonsu Bang, Hyojun Kim, Taesup Moon

ICCV 2021 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 213 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
raise replay mini-batch size from 16 to 64 (ablation)SS-IL · ImageNet-1K T=10average top-1 accuracy: 54.3 -> 68.2Improved
raise replay mini-batch size from 16 to 64 (ablation)SS-IL · ImageNet-1K T=20average top-1 accuracy: 58.8 -> 58.9No clear effect
raise replay mini-batch size from 16 to 64 (ablation)SS-IL · ImageNet-1K T=5average top-1 accuracy: 68.4 -> 68.2No clear effect
raise replay mini-batch size from 16 to 64 (ablation)SS-IL · ImageNet-1K T=10average top-5 accuracy: 86.6 -> 86.0No clear effect
add ER mini-batch replay (ablation)SS-IL · ImageNet-1K T=10, 10k memorybalance of predictions / final-task accuracyImproved
use growing memory (20 per class) instead of fixed 20k memorySS-IL · ImageNet-1K T=10top-1 accuracy drop vs fixed memory: SS-IL 1.3% drop vs EEIL 8.9% dropImproved
SS-IL with 5 samples per class vs baselines with moreSS-IL · ImageNet-1K T=10, base, growing memoryaverage top-1 accuracy: SS-IL 62.3 vs PODNet 57.3 at 10 per classImproved
large base setting vs base setting for SS-ILSS-IL · ImageNet-1K T=10, 10 per classaverage top-1 accuracy: 63.4 -> 60.5Mixed

Later papers that compared with this method

4 later accepted papers report SS-IL as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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