AI Paper Atlas

Research map / Continual learning / Class-incremental

S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning

Jayateja Kalla, Soma Biswas

ECCV 2022 · Continual learning › Class-incremental · approach: Few-shot class-incremental prototypes · 48 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 self-supervision (rotation) to linear classifier (ablation)linear classifier · CIFAR100harmonic mean after final task (%): 26.76 -> 41.80Improved
add self-supervision (rotation) to linear classifier (ablation)linear classifier · CIFAR100top1 accuracy after final task (%): 48.98 -> 53.55Improved
add self-supervision (rotation) to linear classifier (ablation)linear classifier · CIFAR100base task accuracy (%): 74.70 -> 76.14Improved
replace linear classifier with stochastic classifier (ablation)S3C with self-supervision · CIFAR100harmonic mean after final task (%): 41.80 -> 45.22Improved
replace linear classifier with stochastic classifier (ablation)S3C with self-supervision · CIFAR100top1 accuracy after final task (%): 53.55 -> 53.96No clear effect
replace linear classifier with stochastic classifier (ablation)S3C with self-supervision · CIFAR100base task accuracy (%): 76.14 -> 78.03Improved
S3C instead of CECCEC · CIFAR100top1 accuracy (%): 49.14 -> 53.96Improved
S3C instead of CECCEC · miniImageNettop1 accuracy (%): 47.63 -> 52.14Improved
S3C instead of CECCEC · CUB200accuracy at session 10 (%): 52.28 -> 58.95Improved
S3C instead of CECCEC · CUB200performance dropping rate (%): 23.57 -> 20.83Improved
S3C instead of CECCEC · miniImageNetperformance dropping rate: 0.35%Hurt
use only 40 base classes (FSCIL-lb), S3C instead of CECCEC · CIFAR100 (40 base classes)top1 accuracy: 5.29% relative top1, 18.83% HMImproved

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